A multi-type collected data interpolation method and system based on a small sliding window

Abstract

The application relates to a small-sliding-window-based multi-type acquisition data interpolation method and system, which comprises the following steps: S1, acquiring and storing various types of acquisition data to be processed; S2, determining a type acquisition frequency corresponding to the type of the acquisition data; and S3, sequentially interpolating each type of acquisition data based on the type acquisition frequency. The application sets a type sliding window based on the type difference of the acquisition data to meet the differentiated requirements of different types of acquisition data, supports non-uniform acquisition data interpolation obtained in the same time interval based on a small-size sliding window, and can adapt to more complex processing scenes.

Description

[Technical Field]

[0001] This invention belongs to the field of data interpolation technology, and particularly relates to a method and system for interpolating multiple types of acquired data based on a small sliding window. [Background Technology]

[0002] Natural gas refers to all gases that exist naturally in the world, including gases formed by various natural processes in the atmosphere, hydrosphere, and lithosphere. However, the commonly used definition of "natural gas" is a narrower one from an energy perspective, referring to a mixture of hydrocarbon and non-hydrocarbon gases naturally occurring in underground strata. The effective utilization of natural gas energy can improve the absorption capacity of renewable energy and effectively reduce carbon emissions, achieving both economic and social benefits.

[0003] Energy simulation technology can perform detailed simulations of the operating status and control response processes of integrated energy systems, providing data and technical support for energy system planning and design, optimized operation, condition diagnosis, and energy efficiency improvement. It is a key foundational technology for providing integrated energy services. To ensure the safe and maximized utilization of natural gas, operations such as pipeline construction often rely on software simulation models. The simulation of natural gas pipeline networks is based on mathematical models of natural gas flow within the pipelines, and both simulation and modeling are built upon the acquisition of large amounts of accurate and diverse data.

[0004] In data acquisition, testing, and simulation, it is often necessary to compare, analyze, and utilize parameter data recorded by different acquisition devices in parallel. To achieve this comprehensive utilization, it is essential to compare, align, and interpolate parameter values ​​from different devices at the same time. Overcoming the differences between different devices and types of sensors is crucial for meaningful and valuable data utilization. Current technologies typically interpolate acquired data based on key time nodes and the acquisition frequency of the devices, aligning the start times of multiple acquisition devices. However, this time-alignment-based interpolation fails to consider the differences between acquired data, the representation of data values, and, more importantly, the unevenness of acquired data. Therefore, how to perform differentiated interpolation on acquired data from different devices and involving different types of sensors to achieve effective comprehensive utilization of the acquired data is a technical problem that needs to be solved.

[0005] This invention sets up a type sliding window based on the differences in the types of collected data to meet the differentiated needs of different types of data. Based on the small-sized sliding window, it supports interpolation of non-uniform collected data obtained at the same time interval, and can adapt to more complex processing scenarios. [Summary of the Invention]

[0006] To address the aforementioned problems in the prior art, this invention proposes a multi-type data interpolation method based on a small sliding window, the method comprising:

[0007] Step S1: Acquire and store the various types of collected data to be processed;

[0008] Step S2: Determine and collect the type and sampling frequency corresponding to the data type;

[0009] Step S3: Interpolate the collected data for each type based on the type acquisition frequency;

[0010] Step S4: Perform simulation based on the interpolation results, and adjust the type acquisition frequency based on the accuracy of the simulation results.

[0011] Furthermore, step S3 includes the following steps;

[0012] Step S31: Obtain a type of data to be processed and its corresponding type acquisition frequency;

[0013] Step S32: Type-based frequency FT acquisition i Determine the type of time window WN i Specifically: Set the type time window length. Among them: RN i This is the preset number of data entries to be collected;

[0014] Step S33: Interpolate the collected data within the type time window length;

[0015] Step S34: Determine whether the collected data has been processed. If not, continue sliding the type time window and return to step S32; if yes, proceed to the next step.

[0016] Step S35: Determine whether all types have been processed. If yes, step S3 ends; otherwise, return to step S31.

[0017] Furthermore, step S33 specifically includes the following steps:

[0018] Step S331: Slide the type time window starting from the beginning of the collected data;

[0019] Step S332: Determine the number of data entries collected within the current type of time window CuWn_RN i Is it greater than or equal to the preset number of data entries RN? i If so, do not perform interpolation and proceed to step S34; otherwise, proceed to the next step.

[0020] Step S333: Determine the interpolation position within the type time window; specifically: determine the position with the largest time interval between two adjacent collected data points within the type time window (RN). i -CuWn_RN i The midpoint position corresponding to each time interval is used as the interpolation position;

[0021] Step S334: For the adjacent collected data Dt at the interpolation position k and Dt k+1 Calculate the interpolation DI; specifically: set the interpolation DI = (Dt) k +Dt k+1 ) / 2;

[0022] Step S335: Place the interpolation at the interpolation location; specifically: insert the interpolation DI into the acquired data Dt. k and Dt k+1 Between, and with Dt k and Dt k+1 The corresponding collection timestamps are associated with intermediate time points.

[0023] Furthermore, an accuracy rate of 99.9% is required.

[0024] Furthermore, different types of collected data are stored separately.

[0025] A multi-type data acquisition interpolation system based on a small sliding window, the system comprising: a user terminal and an interpolation server;

[0026] The user terminal enables the user to send a propagation path analysis request to the interpolation server;

[0027] The interpolation server is used to execute the multi-type data acquisition interpolation method based on a small sliding window.

[0028] A big data system for interpolating multi-type acquired data based on a small sliding window, the system comprising: a user terminal and a big data node;

[0029] User terminals and big data interpolation nodes;

[0030] The user terminal enables the user to send a propagation path analysis request to the big data interpolation node;

[0031] The big data interpolation node is used to perform the above-mentioned multi-type data interpolation method based on a small sliding window.

[0032] A processor for running a program, wherein the program executes the multi-type acquisition data interpolation method based on a small sliding window during runtime.

[0033] A computer-readable storage medium includes a program that, when run on a computer, causes the computer to perform the described multi-type acquisition data interpolation method based on a small sliding window.

[0034] An execution device includes a processor coupled to a memory storing program instructions that, when executed by the processor, implement the multi-type acquisition data interpolation method based on a small sliding window.

[0035] The beneficial effects of this invention include:

[0036] (1) Set up and collect differential basic interpolation windows related to data types, and support numerical interpolation of non-uniformly collected data obtained by sliding the window at uniform time intervals, which can adapt to more complex processing scenarios; (2) Propose a small sliding window length, and use a simple interpolation position and difference data value calculation method based on periodic interval attempts to obtain relatively accurate interpolation results with less computational overhead; (3) Adjust the collection frequency based on the correctness of simulation results to improve the data space of interpolation operation to cooperate with simulation applications. [Attached Image Description]

[0037] The accompanying drawings, which are provided to further illustrate the invention and form part of this application, are not intended to unduly limit the invention. In the drawings:

[0038] Figure 1 This is a schematic diagram of the multi-type acquisition data interpolation method based on a small sliding window according to the present invention.

Detailed Implementation Methods

[0039] In the description of this invention, the use of terms such as "first," "second," etc., is merely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of technical features indicated, or implicitly indicating the order of the technical features indicated.

[0040] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0041] As attached Figure 1 As shown, this invention proposes a multi-type data interpolation method based on a small sliding window, the method comprising the following steps:

[0042] Step S1: Acquire and store the various types of collected data to be processed;

[0043] Preferred method: Store different types of collected data separately;

[0044] Preferably, the types of data collected include: concentration, pressure, flow rate, temperature, sound, valve status, etc.

[0045] Preferably, the collected data is natural gas pipeline network data;

[0046] Preferably, the collected data and the collection timestamp are stored together, and the timestamp is provided by the collection device;

[0047] Preferably, the data acquisition device is provided via short-range wireless communication or long-range wireless communication.

[0048] Preferably, the short-range wireless communication is Bluetooth communication.

[0049] Preferably, the long-distance wireless communication is a WIFI communication method;

[0050] Preferably, the data acquisition device is a sensor device;

[0051] Step S2: Determine and collect the type and sampling frequency corresponding to the data type;

[0052] Preferably, the acquisition frequency is the lowest acquisition frequency related to the type of data being acquired; here, "lowest" can be the lowest effective operating frequency of different sensors, the lowest acquisition frequency corresponding to the frequency of data change, the lowest acquisition frequency set in the simulation model, etc.

[0053] Preferably, the type acquisition frequency is a type acquisition frequency related to the simulation method of the simulation model;

[0054] Step S3: Interpolate the collected data for each type based on the type acquisition frequency;

[0055] Step S3 includes the following steps;

[0056] Step S31: Obtain a type of data to be processed and its corresponding type acquisition frequency;

[0057] Preferably, the collected data is data prepared for processing; for example, collected data acquired within the most recent first time interval.

[0058] Preferably, the processing is simulation processing, prediction processing, etc.

[0059] Step S32: Type-based frequency FT acquisition i Determine the type of time window WN i Specifically: Set the type time window length. Among them: RN i This is the preset number of data entries to be collected;

[0060] Replaceable: RNi This is the preset number of data collections, where i is the type number;

[0061] Preferred: RN i This refers to the number of data points that form valid interpolations for the i-th type of collected data; in other words, to form a valid attempt or prediction, subsequent interpolations of the i-th type of collected data must be based on at least RN. i Number of data entries collected;

[0062] Preferred method: Set the same preset number of data collections for each type;

[0063] Preferred: Setting RN i =10;

[0064] Step S33: Interpolate the collected data within the type time window length;

[0065] Step S33 specifically includes the following steps:

[0066] Step S331: Slide the type time window starting from the beginning of the collected data;

[0067] Step S332: Determine the number of data entries collected within the current type of time window CuWn_RN i Is it greater than or equal to the preset number of data entries RN? i If so, do not perform interpolation and proceed to step S34; otherwise, proceed to the next step.

[0068] Because the acquisition of data within a uniform time interval is not uniform, even for the same data type, the number of data entries collected within the current type time window changes in real time.

[0069] Step S333: Determine the interpolation position within the type time window; specifically: determine the position with the largest time interval between two adjacent collected data points within the type time window (RN). i -CuWn_RN i The midpoint positions corresponding to ) time intervals are used as interpolation positions; that is, there are (RN) interpolation positions. i -CuWn_RN i )indivual;

[0070] Step S334: For the adjacent collected data Dt at the interpolation position k and Dt k+1 Calculate the interpolation DI; specifically: set the interpolation DI = (Dt) k +Dt k+1 ) / 2;

[0071] Alternative: Calculate the interpolation DI based on a finite number of periodic attempts; specifically including the following steps;

[0072] Step Sub1: Calculate the periodic mean It using the following formula. NT,j ;

[0073]

[0074] Where: NT is the period interval; j is the j-th position in the NT period; j = 1 to NT; the unit of the period is the number of data entries or the number of data entries; the period is used to try to discover local changes in the collected data; and the j value is used to describe the specific changes in the data within the period;

[0075] Below are examples for NT=2 and NT=3;

[0076]

[0077]

[0078]

[0079]

[0080]

[0081] Step Sub2: Calculate the peak difference and SmSb corresponding to different period intervals x. x ;

[0082] SmSb x =|∑ j (It x,j -It x,j-1 )|,j=2~x; where: x=2~NT; select the periodic mean It corresponding to the peak difference and the largest one. maxNT,j Where: maxNT is the period interval corresponding to the largest one;

[0083] Step Sub3: Determine the first piece of data Dt from the adjacent collected data. k Start by collecting m data points in the same direction, and obtain the corresponding collected data Dt. k-m+1 ,…,Dt k ;

[0084] The direction of change is the direction of numerical change, such as: increasing, decreasing, or remaining unchanged;

[0085] Step Sub4: Determine the interpolation DI based on the following formula;

[0086]

[0087] In existing technologies, difference data prediction is often based on fitting functions or averages. However, using fitting functions for difference calculations is obviously too costly for the time window length. On the other hand, using averages for difference calculations easily ignores the periodic characteristics of the data. This invention proposes a difference calculation method based on simple periodic prediction for small sliding window lengths, which obtains relatively accurate interpolation results with less computational overhead.

[0088] Step S335: Place the interpolation at the interpolation location; specifically: insert the interpolation DI into the acquired data Dt. k and Dt k+1 Between, and with Dt k and Dt k+1 The corresponding collection timestamps are associated with intermediate time points;

[0089] Step S34: Determine whether the collected data has been processed. If not, continue sliding the type time window and return to step S32; if yes, proceed to the next step.

[0090] Preferred setting: Set the sliding step size to be equal to 1 / 2 the length of the type time window;

[0091] Alternative: Set the sliding step size to equal the length of one type of time window;

[0092] Step S35: Determine whether all types have been processed. If yes, step S3 ends; otherwise, return to step S31.

[0093] Step S4: Perform simulation based on the interpolation results, and adjust the type acquisition frequency based on the accuracy of the simulation results; when the accuracy meets the requirements, do not adjust the type acquisition frequency; when the accuracy does not meet the requirements, increase the type acquisition frequency; specifically: input the interpolated acquisition data into the simulation model to obtain the simulation results corresponding to the acquisition data; perform multiple simulations and calculate the cumulative accuracy corresponding to the multiple simulation results; determine whether the cumulative accuracy is greater than the required accuracy; if so, do not adjust the type acquisition frequency and proceed to the next step; otherwise, increase the type acquisition frequency and return to step S3;

[0094] Preferably, the required accuracy is 99.9%;

[0095] The method further includes step S5: inputting the interpolated collected data into a neural network model to obtain natural gas pipeline network monitoring results based on the collected data; and evaluating the status of the natural gas pipeline network based on the monitoring results.

[0096] Preferably, the state includes a safe state;

[0097] Preferably, the state is a binary state, either normal or abnormal;

[0098] Based on the same inventive concept, this invention proposes a multi-type data acquisition interpolation system based on a small sliding window, the system comprising the following steps: a user terminal and an interpolation server;

[0099] The user terminal enables the user to send a propagation path analysis request to the interpolation server;

[0100] The interpolation server is used to execute the above-described multi-type data interpolation method based on a small sliding window;

[0101] Based on the same inventive concept, this invention proposes a big data system for interpolating multi-type acquired data based on a small sliding window. The system includes the following steps: a user terminal and a big data interpolation node.

[0102] The user terminal enables the user to send a propagation path analysis request to the big data interpolation node;

[0103] The big data interpolation node is used to execute the above-mentioned multi-type data interpolation method based on a small sliding window.

[0104] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but does not necessarily, correspond to a file in a file system. A program can be stored as part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to said program, or in multiple co-located files (e.g., a file storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on a single computer or on multiple computers located at a single site or distributed across multiple sites and interconnected by a communications network.

[0105] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0107] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0108] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-type data interpolation method based on a small sliding window, characterized in that, include: Step S1: Acquire and store various types of energy simulation data to be processed; Step S2: Determine and collect the type and sampling frequency corresponding to the data type; Step S3: Interpolate the collected data for each type based on the type acquisition frequency; The interpolation DI is calculated based on a finite number of periodic attempts; specifically: Step Sub1: Calculate the periodic mean It using the following formula. NT,j ; ； in: NT is the number of data entries collected within the current time window; NT is the period interval; j is the j-th position in the NT period; j = 1 to NT; the unit of the period is the number of data entries or the number of collections; the period is used to try to discover local changes in the collected data; the j value describes the specific changes in the data within the period; Step Sub2: Calculate the peak difference and SmSb corresponding to different period intervals x. x ; SmSb x =|∑ j (It x,j -It x,j-1 )|,j=2~x; where: x=2~NT; select the periodic mean It corresponding to the peak difference and the largest one. maxNT,j Where: maxNT is the period interval corresponding to the largest one; Step Sub3: Determine the first piece of data Dt from the adjacent collected data. k Start by collecting m data points in the same direction, and obtain the corresponding collected data Dt. k-m+1 ,…,Dt k ; Step Sub4: Determine the interpolation DI based on the following formula; ； Step S4: Perform simulation based on the interpolation results, and adjust the type acquisition frequency based on the accuracy of the simulation results.

2. The multi-type data interpolation method based on a small sliding window according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Obtain a type of data to be processed and its corresponding type acquisition frequency; Step S32: Type-based frequency FT acquisition i Determine the type of time window WN i Specifically: Set the type time window length. Among them: RN i This is the preset number of data entries to be collected; Step S33: Interpolate the collected data within the type time window length; Step S34: Determine whether the collected data has been processed. If not, continue sliding the type time window and return to step S32; if yes, proceed to the next step. Step S35: Determine whether all types have been processed. If yes, step S3 ends; otherwise, return to step S31.

3. The multi-type data interpolation method based on a small sliding window according to claim 2, characterized in that, Step S33 specifically includes the following steps: Step S331: Slide the type time window starting from the beginning of the collected data; Step S332: Determine the number of data entries collected within the current type of time window CuWn_RN i Is it greater than or equal to the preset number of data entries RN? i If so, do not perform interpolation and proceed to step S34; otherwise, proceed to the next step. Step S333: Determine the interpolation position within the type time window; specifically: determine the position with the largest time interval between two adjacent collected data points within the type time window (RN). i -CuWn_RN i The midpoint position corresponding to each time interval is used as the interpolation position; Step S334: For the adjacent collected data Dt at the interpolation position k and Dt k+1 Calculate the interpolation DI; set the interpolation DI = (Dt) k +Dt k+1 ) / 2; Step S335: Place the interpolation at the interpolation location; specifically: insert the interpolation DI into the acquired data Dt. k and Dt k+1 Between, and with Dt k and Dt k+1 The corresponding collection timestamps are associated with intermediate time points.

4. The multi-type data interpolation method based on a small sliding window according to claim 3, characterized in that, The required accuracy is 99.9%.

5. The multi-type data interpolation method based on a small sliding window according to claim 4, characterized in that, Different types of collected data are stored separately.

6. A multi-type data acquisition interpolation system based on a small sliding window, characterized in that, The system includes: a user terminal and an interpolation server; The user terminal enables the user to send a propagation path analysis request to the interpolation server; The interpolation server is used to execute the multi-type acquisition data interpolation method based on a small sliding window as described in any one of claims 1-5.

7. A big data system for interpolating multi-type acquired data based on a small sliding window, characterized in that, The system includes: user terminals and big data nodes; User terminals and big data interpolation nodes; The user terminal enables the user to send a propagation path analysis request to the big data interpolation node; The big data interpolation node is used to execute the multi-type data interpolation method based on a small sliding window as described in any one of claims 1-5.

8. A processor, characterized in that, The processor is used to run a program, wherein the program executes the multi-type acquisition data interpolation method based on a small sliding window as described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, Includes a program that, when run on a computer, causes the computer to perform the multi-type acquisition data interpolation method based on a small sliding window as described in any one of claims 1-5.

10. An execution device, characterized in that, The system includes a processor coupled to a memory, the memory storing program instructions, which, when executed by the processor, implement the multi-type acquisition data interpolation method based on a small sliding window as described in any one of claims 1-5.

Images