A method, device and equipment for processing data of soft test points in industrial system

By extending the system dynamics model, the calculation method of unmeasurable points in industrial systems is derived and automatic calculation is solved, and the problem of low data acquisition efficiency of unmeasurable points is realized, and automatic transparent acquisition and abnormal detection of data are realized.

CN118520407BActive Publication Date: 2024-11-08BEIJING IND BIG DATA INNOVATION CENT CO LTD +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410985753.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-08
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

In industrial systems, some measurement points are missing due to cost or equipment failure, making them unmeasurable points. The existing soft measurement methods are cumbersome and inefficient in calculations.

Method used

By extending the system dynamics model, the impact grouping and function calculation relationship of unmeasurable points are determined, the calculation method is derived, and the calculation method is automatically calculated during user query, and distribution statistics are performed on multiple result sets to detect abnormal outlier result sets.

Benefits of technology

It realizes automatic and transparent acquisition of unmeasured point data in industrial systems, improving data acquisition efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118520407B_ABST
    Figure CN118520407B_ABST
Patent Text Reader

Abstract

The present invention provides a data processing method, device and equipment for soft-measurement points in an industrial system, which belongs to the technical field of industrial system information processing and solves the problem of data acquisition of unmeasurable points in industrial systems. The method includes: obtaining target unmeasurable point data and influence relationships by extending the system dynamics model; wherein the extended system dynamics model includes influence groups of the target unmeasurable point data, and function calculation relationships and monotonicity of functions between multiple measurable points and unmeasurable points in the influence groups; deriving a calculation method for the target unmeasurable point according to the extended system dynamics model; automatically performing calculations according to the calculation method for the target unmeasurable point to respond to user queries; when there are multiple result sets for the target unmeasurable point, performing distribution statistics on the multiple result sets to realize abnormal outlier result set detection. The technical solution of the present invention realizes automatic and transparent acquisition of unmeasurable point data in industrial systems.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of industrial system information processing, and in particular to a method, device and equipment for processing data of soft test points in an industrial system. Background Art

[0002] In the process of data analysis for industrial systems (including equipment operation and manufacturing), it is necessary to obtain the system's measurement point data. Due to cost, feasibility and other reasons (such as sensors not being installed, or sensors being damaged and causing data to be unavailable), some measurement points have missing data, and such measurement points can be called unmeasurable points; and the industrial system is a strong mechanism system, and the data of some unmeasurable points can be derived and calculated from other measurement points. This derivation process can be called "soft measurement". At present, soft measurements of unmeasurable points in industrial systems often require a series of operations such as mechanism analysis, data cleaning, and data calculation to obtain them. There are problems such as cumbersome and repetitive calculation processes and low efficiency. Summary of the invention

[0003] The present invention provides a data processing method, device and equipment for soft-measurement points in an industrial system, which solves the problem of data acquisition of unmeasurable points in the industrial system.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] An embodiment of the present invention provides a data processing method for a soft test point in an industrial system, comprising:

[0006] The target unmeasurable point data and influence relationship are obtained by extending the system dynamics model; wherein the extended system dynamics model includes: the influence grouping of the target unmeasurable point data, and the function calculation relationship and the monotonicity of the function between multiple measurable points and unmeasurable points in the influence grouping; the influence grouping includes multiple measurable points, and the multiple measurable points have influence relationships with the target unmeasurable points, and the influences of different influence groups on the target unmeasurable points are independent of each other;

[0007] According to the extended system dynamics model, a calculation method of the target unmeasurable point is derived;

[0008] Automatically perform calculations according to the calculation method of the target unmeasurable point and respond to user queries;

[0009] When there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to achieve abnormal outlier result set detection.

[0010] Optionally, the target unmeasurable point data and influence relationship are obtained by extending the system dynamics model, including:

[0011] According to the extended system dynamics model, target unmeasurable point data of the extended system dynamics model are determined; wherein the target unmeasurable point data include indicator variables of the target unmeasurable point and mechanism influence relationships between the target unmeasurable point and other measurement point variables in the extended system dynamics model.

[0012] Optionally, the impact grouping of the target unmeasurable point data includes:

[0013] A plurality of measurable points associated with the target unmeasurable point, and a plurality of operation expressions obtained according to association relationships between the indicator variables corresponding to the target unmeasurable point and the plurality of indicator variables corresponding to the associated plurality of measurable points;

[0014] Among them, the indicator variable corresponding to the target unmeasurable point is the dependent variable of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; the multiple measurable points corresponding to the independent variables in an operation expression constitute an influence group.

[0015] Optionally, according to the extended system dynamics model, a calculation method for deriving the target unmeasurable point includes:

[0016] Determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model;

[0017] Combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression;

[0018] According to the calculation path, a calculation method for the target unmeasurable point is obtained.

[0019] Optionally, all associated measuring points of the target unmeasurable point are combined according to the impact grouping to obtain a calculation path, including:

[0020] In the extended system dynamics model, starting from the location of the target unmeasurable point, all associated measuring points of the target unmeasurable point are traversed in sequence, and combined according to the impact grouping to obtain a measuring point set V tree And the topological relationship set L between the measuring points tree ;

[0021] According to the measuring point set V tree and the topological relationship set L tree , and sequentially construct the path set L between the target unmeasurable point and each measuring point, L={V tree ∪L tree};

[0022] According to the path set L, a calculation path is obtained.

[0023] Optionally, automatically performing calculations according to the calculation method of the target unmeasurable point to respond to user queries includes:

[0024] Determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable;

[0025] If the target unmeasurable point can be calculated, the calculation results of each calculation path are output in turn to obtain multiple result sets R of the target unmeasurable point;

[0026] Output multiple result sets R of the target unmeasurable points to respond to user queries.

[0027] Optionally, when there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to implement abnormal outlier result set detection, including:

[0028] Calculate the mean and standard deviation of multiple result sets R of the target unmeasurable point;

[0029] Comparing the standard deviation with a first preset value to obtain a comparison result;

[0030] According to the comparison result, the index data of the target unmeasurable point is obtained.

[0031] An embodiment of the present invention further provides a data processing device for a soft test point in an industrial system, the data processing device comprising:

[0032] A modeling module, used to obtain target unmeasurable point data and influence relationships by extending the system dynamics model; wherein the extended system dynamics model includes: influence groups of the target unmeasurable point data, and function calculation relationships and monotonicity of functions between multiple measurable points and unmeasurable points in the influence groups; the influence groups include multiple measurable points, and the multiple measurable points have influence relationships with the target unmeasurable points, and the influences of different influence groups on the target unmeasurable points are independent of each other;

[0033] A reasoning module, used for deriving a calculation method of a target unmeasurable point according to the extended system dynamics model;

[0034] A query module, used to automatically perform calculations according to the calculation method of the target unmeasurable points and respond to user queries;

[0035] The anomaly detection module is used to perform distribution statistics on the multiple result sets when there are multiple result sets for the target unmeasurable point, so as to realize abnormal outlier result set detection.

[0036] Optionally, the target unmeasurable point data and influence relationship are obtained by extending the system dynamics model, including:

[0037] According to the extended system dynamics model, target unmeasurable point data of the extended system dynamics model are determined; wherein the target unmeasurable point data include indicator variables of the target unmeasurable point and mechanism influence relationships between the target unmeasurable point and other measurement point variables in the extended system dynamics model.

[0038] Optionally, the impact grouping of the target unmeasurable point data includes:

[0039] A plurality of measurable points associated with the target unmeasurable point, and a plurality of operation expressions obtained according to association relationships between the indicator variables corresponding to the target unmeasurable point and the plurality of indicator variables corresponding to the associated plurality of measurable points;

[0040] Among them, the indicator variable corresponding to the target unmeasurable point is the dependent variable of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; the multiple measurable points corresponding to the independent variables in an operation expression constitute an influence group.

[0041] Optionally, according to the extended system dynamics model, a calculation method for deriving the target unmeasurable point includes:

[0042] Determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model;

[0043] Combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression;

[0044] According to the calculation path, a calculation method for the target unmeasurable point is obtained.

[0045] Optionally, all associated measuring points of the target unmeasurable point are combined according to the impact grouping to obtain a calculation path, including:

[0046] In the extended system dynamics model, starting from the location of the target unmeasurable point, all associated measuring points of the target unmeasurable point are traversed in sequence, and combined according to the impact grouping to obtain a measuring point set V tree And the topological relationship set L between the measurement points tree ;

[0047] According to the measuring point set V tree and the topological relationship set L tree , and sequentially construct the path set L between the target unmeasurable point and each measuring point, L={Vtree ∪L tree};

[0048] According to the path set L, a calculation path is obtained.

[0049] Optionally, automatically performing calculations according to the calculation method of the target unmeasurable point to respond to user queries includes:

[0050] Determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable;

[0051] If the target unmeasurable point can be calculated, the calculation results of each calculation path are output in turn to obtain multiple result sets R of the target unmeasurable point;

[0052] Output multiple result sets R of the target unmeasurable points to respond to user queries.

[0053] Optionally, when there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to implement abnormal outlier result set detection, including:

[0054] Calculate the mean and standard deviation of multiple result sets R of the target unmeasurable point;

[0055] Comparing the standard deviation with a first preset value to obtain a comparison result;

[0056] According to the comparison result, the index data of the target unmeasurable point is obtained.

[0057] An embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program executes the above method when executed by the processor.

[0058] An embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method.

[0059] The technical solution of the present invention includes at least the following effects:

[0060] The data processing method of soft-measurement points in an industrial system of the present invention obtains target unmeasurable point data and influence relationships by extending the system dynamics model; wherein the extended system dynamics model includes: influence groups of target unmeasurable point data, and function calculation relationships and monotonicity of functions between multiple measurable points and unmeasurable points in the influence groups; the influence groups include multiple measurable points, and multiple measurable points have influence relationships with target unmeasurable points, and influences of different influence groups on target unmeasurable points are independent of each other; according to the extended system dynamics model, a calculation method for target unmeasurable points is derived; according to the calculation method for target unmeasurable points, calculations are automatically performed to respond to user queries; when there are multiple result sets for the target unmeasurable points, distribution statistics are performed on the multiple result sets to realize abnormal outlier result set detection, thereby realizing automatic and transparent acquisition of unmeasurable point data in the industrial system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flow chart of a data processing method for a soft test point in an industrial system provided by an embodiment of the present invention;

[0062] Figure 2 is a structural diagram of a system dynamics model of a generator wire rod water cooling system provided by an embodiment of the present invention;

[0063] Figure 3 is an influence relationship diagram of each measuring point of the system dynamics model of the generator wire rod water cooling system provided by an embodiment of the present invention;

[0064] Figure 4 It is a first subgraph of the calculation relationship of each measuring point of the system dynamics model of the generator wire rod water cooling system provided by an embodiment of the present invention;

[0065] Figure 5 It is a second subgraph of the calculation relationship of each measuring point of the system dynamics model of the generator wire rod water cooling system provided by an embodiment of the present invention;

[0066] Figure 6 is a third subgraph of the calculation relationship of each measuring point of the system dynamics model of the generator wire rod water cooling system provided by an embodiment of the present invention;

[0067] Figure 7 is a fourth sub-graph of the calculation relationship of each measuring point of the system dynamics model of the generator wire rod water cooling system provided by an embodiment of the present invention;

[0068] Figure 8 It is a schematic diagram of a soft measurement calculation process of a data processing method of a soft measurement point in an industrial system provided by an embodiment of the present invention;

[0069] Fig. 9 It is a schematic diagram of a soft measurement query process of a data processing method for a soft measurement point in an industrial system provided by an embodiment of the present invention;

[0070] Fig.10 It is a structural diagram of a data processing device for soft test points in an industrial system provided by an embodiment of the present invention;

[0071] Fig.11 It is a schematic diagram of the structure of a computing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0073] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0074] like Figure 1 As shown, an embodiment of the present invention proposes a data processing method for a soft test point in an industrial system, comprising:

[0075] Step 11, obtaining target unmeasurable point data and influence relationships by extending the system dynamics model; wherein the extended system dynamics model includes: influence groups of the target unmeasurable point data, and function calculation relationships and monotonicity of functions between multiple measurable points and unmeasurable points in the influence groups; the influence groups include multiple measurable points, and the multiple measurable points have influence relationships with the target unmeasurable points, and the influences of different influence groups on the target unmeasurable points are independent of each other;

[0076] For example, Figure 2 As shown in the figure, a system dynamics model of a generator wire rod water cooling system includes multiple measurable points A 1 ~A 4 and A 7 , the corresponding indicator data are: cooling water flow rate, cooling water pipe cross-sectional area, cooling water pipe pressure difference, cooling water pipe narrow cross-sectional area, wire rod temperature, etc., unmeasurable point A 5 The indicator data is the cooling water flow rate, and the unmeasurable point A6 The indicator data is water resistance, but the cooling water flow rate is related to the cooling water flow rate, the cross-sectional area of ​​the cooling water pipe, the pressure difference of the cooling water pipe, the cross-sectional area of ​​the narrow part of the cooling water pipe, the wire rod temperature, and the water resistance. In this way, a network structure relationship map will be formed between the unmeasurable points and the measurable points in the whole industrial system dynamics model;

[0077] Step 12, deriving a calculation method of the target unmeasurable point according to the extended system dynamics model;

[0078] Step 13, automatically performing calculations according to the calculation method of the target unmeasurable point and responding to user queries;

[0079] Step 14: When there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to achieve abnormal outlier result set detection.

[0080] In this embodiment, firstly, the target unmeasurable point data is acquired by extending the system dynamics model; wherein, the unmeasurable point refers to a point in the industrial system where data is missing due to the lack of sensor installation or sensor damage, and the point becomes an unmeasurable point; the extended system dynamics model includes a relationship map between multiple measurable points and unmeasurable points; this embodiment determines the measurable point data that affects the unmeasurable point by extending the system dynamics model, and automatically calculates the indicator data of the unmeasurable point based on the corresponding measurable point data, responds to user queries, and when there are multiple result sets for the target unmeasurable point, distributes and counts the multiple result sets to detect abnormal outlier result sets, thereby realizing automatic and transparent acquisition of unmeasurable point data in the industrial system.

[0081] In an optional embodiment of the present invention, step 11 may include:

[0082] Step 111, determining target unmeasurable point data of the extended system dynamics model according to the extended system dynamics model; wherein the target unmeasurable point data includes indicator variables of the target unmeasurable point and mechanism influence relationships between the target unmeasurable point and other measurement point variables in the extended system dynamics model.

[0083] In this embodiment, the target unmeasurable point data of the industrial system dynamics model can be obtained through the relationship map; 5 For example, according to Figure 2 The relationship diagram shown can determine the unmeasurable point A 5 Position in the relationship graph of the network structure and unmeasurable point A 5 The corresponding indicator data is the cooling water flow rate, recorded as the indicator variable x 5 .

[0084] In an optional embodiment of the present invention, the impact grouping of the target unmeasurable point data includes:

[0085] Multiple measurable points associated with the target unmeasurable point, and multiple operation expressions obtained according to the association relationship between the indicator variable corresponding to the target unmeasurable point and the multiple indicator variables corresponding to the associated multiple measurable points; wherein the indicator variable corresponding to the target unmeasurable point is the dependent variable of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; multiple measurable points corresponding to the independent variables in one operation expression constitute an influence group.

[0086] Specifically, in Figure 2 In the system dynamics model of the generator bar water cooling system shown in the figure, the target unmeasurable point A 5 The corresponding indicator data is the cooling water flow rate, which is recorded as the indicator variable x 5 ; Measurement point A 1 ~A 4 , A 7 All are the same as measuring point A 5 Measurable point with influence relationship, measuring point A 1 ~A 4 , A 7 The corresponding indicator data are cooling water flow rate, cooling water pipe cross-sectional area, cooling water pipe pressure difference, cooling water pipe narrow cross-sectional area, and wire rod temperature, which are recorded as indicator variables x 1 ~x 4 、x 7 According to the velocity area calculation method, the cooling water flow rate can be calculated through the index data: cooling water flow rate and cooling water pipe cross-sectional area. The calculation expression is: x 5 =f(x 1 , x 2 ); where f is the velocity area calculation function; according to the differential pressure calculation method, the cooling water flow rate can also be calculated through the index data: the pressure difference of the cooling water pipe and the cross-sectional area of ​​the narrow part of the cooling water pipe. The calculation expression is expressed as: x 5 =g(x 3 , x 4 ); where g is the differential pressure calculation function; under the premise of constant cooling water temperature, there is a monotonic relationship between cooling water flow and wire rod temperature, and its operation expression can be expressed as: x 5 = t(x 7 ); where t is a calculation function obtained by experimental fitting; according to the above multiple operation expressions, it can be determined that the impact groups of the target unmeasurable point data are {A 1 , A 2}, { A 3 , A4}, { A 7},like Figure 3 As shown in the figure, multiple measurable points corresponding to the independent variables in one operation expression constitute an impact group, x 5 is the dependent variable, x 1 ~x 4 、x 7 is the independent variable.

[0087] In an optional embodiment of the present invention, step 12 may include:

[0088] Step 121, determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model;

[0089] Step 122, combining all the associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression;

[0090] Step 123, obtaining a calculation method for the target unmeasurable point according to the calculation path.

[0091] Specifically, in Figure 2 In the system dynamics model of the generator bar water cooling system shown in the figure, from the target unmeasurable point A 5 Starting from the location, all the associated measuring points of the target unmeasurable point are traversed in sequence, and it can be determined that all the associated measuring points also include the unmeasurable point A 6 , unmeasurable point A 6 The corresponding indicator data is water resistance, which is recorded as the indicator variable x 6 ; Under the premise of constant pump power, there is a monotonic relationship between cooling water flow and water resistance, and its operation expression can be expressed as: x 6 =h -1 (x 5 ), or x 5 = h(x 6 ); where h is a calculation function, which can be obtained by fitting based on the experimental results of the test machine; thus, the unmeasurable point A is obtained 5 All associated measurement points are A 1 ~A 4 , A 6 , A 7 , denoted as the measurement point set V tree , the topological relationship between the measurement points is recorded as set L tree , where the topological relationship set L tree Contains the influence grouping data of the measuring points and the monotonicity data of the operation function, according to the measuring point set V tree And the topological relationship set L tree, and sequentially construct the calculation relationship graph between the target unmeasurable point and each measuring point, recorded as the path set L, L={V tree ∪L tree}, according to the path set L, all the operation expressions of the target unmeasurable points can be obtained, and at the same time, Figure 2 The relationship graph shown is divided into multiple subgraphs, such as Figures 4 to 7 As shown, each subgraph includes multiple measurement points and the topological relationships of multiple measurement points. If there are n monotonic functions, the number of subgraphs is 2. n , for each calculation path, the calculation method of the target unmeasurable point is finally obtained.

[0092] In an optional embodiment of the present invention, step 13 may include:

[0093] Step 131, determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable;

[0094] Step 132, if the target unmeasurable point can be calculated, then the calculation results of each calculation path are output in sequence to obtain multiple result sets R of the target unmeasurable point;

[0095] Step 133: output multiple result sets R of the target unmeasurable points to respond to user queries.

[0096] Specifically, in Figure 2 In the system dynamics model of the generator bar water cooling system shown in FIG. 1 , according to the path set L, the unmeasurable point A can be obtained. 5 and A 6 The calculation paths are: 5 =f(x 1 , x 2 ) or x 5 =g(x 3 , x 4 ) or x 5 = t(x 7 );x 6 =h -1 (x 5 ) = h -1 [f(x 1 , x 2 )] or x 6 =h -1 (x 5 ) = h -1 [g(x 3 , x 4 ) or x 6 =h -1 (x 5 ) = h-1 [t(x 7 )], so point A is unmeasurable 5 and A 6 The number of calculation paths is 3, and point A cannot be measured. 5 and A 6 All of them are calculable measurement points. The calculation results of each calculation path are output in turn, and the result set R of the unmeasurable point "cooling water flow" is obtained. 5 and the result set R of "water resistance" 6 , output result set R 5 or R 6 , in response to user queries.

[0097] In an optional embodiment of the present invention, step 14 may include:

[0098] Step 141, calculating the mean and standard deviation of multiple result sets R of the target unmeasurable point;

[0099] Step 142, comparing the standard deviation with a first preset value to obtain a comparison result;

[0100] Step 143: Obtain the index data of the target unmeasurable point according to the comparison result.

[0101] Specifically, the result set R 5 Take the target unmeasurable point result set R as an example. 5 The mean and standard deviation of the calculation paths are compared with the preset value. When the standard deviation is less than the preset value, it means that the calculation results of each calculation path are slightly different, and the mean value can be used as the indicator data of the target unmeasurable point. When the standard deviation is greater than or equal to the preset value, it means that the calculation results of each calculation path are quite different, and the result set R is selected. 5 The calculation result with the largest difference from the mean is excluded, the mean and standard deviation of the result set are recalculated and the above detection process is repeated until the standard deviation is less than the preset value, and the mean at this time is used as the indicator data of the target unmeasurable point.

[0102] Furthermore, in an embodiment of the present invention, before step 11, the following steps may be included:

[0103] Step 10, receiving a query request for target unmeasurable point data of an industrial system dynamics model; the query request carries: the index data to be output of the target unmeasurable point; and the index data of multiple measurable points are stored in a basic measurement point time series database.

[0104] In a specific implementation example, the query method for unmeasurable points includes: a user requests a given measuring point, and obtains a calculation function of the measuring point by calculating a relationship graph; the calculation function is translated into: a query statement for one or more basic measuring points; a query is executed on a time series database of basic measuring point data, and a query result is returned to the term, such as Figure 8 and Fig. 9 For example, to obtain the unmeasurable point A 6 The indicator data process includes:

[0105] # Read measurable points from the time series database

[0106] df = read_tsdb(tags=['flow rate', 'cross-sectional area', 'pressure difference', 'cross-sectional area of ​​narrow part', 'wire rod temperature'])

[0107] # Cooling water flow calculation method 1

[0108] def flow1(row):

[0109] return f(row['flow velocity'], row['cross-sectional area'])

[0110] # Cooling water flow calculation method 2

[0111] def flow1(row):

[0112] return g(row['pressure difference'], row['cross-sectional area of ​​narrow part'])

[0113] # Cooling water flow calculation method 3

[0114] def flow3(row):

[0115] return t_inverse(row['wire rod temperature'])

[0116] # Cooling water pipe water resistance calculation method 1

[0117] def pipe_block1(row):

[0118] return h_inverse(flow1(row))

[0119] # Cooling water pipe water resistance calculation method 2

[0120] def pipe_block1(row):

[0121] return h_inverse(flow2(row))

[0122] # Cooling water pipe water resistance calculation method 3

[0123] def pipe_block1(row):

[0124] return h_inverse(flow3(row))

[0125] df['flow1'] = df.apply(flow1)

[0126] df['flow2'] = df.apply(flow2)

[0127] df['flow3'] = df.apply(flow3)

[0128] df['pipe_block1'] = df.apply(pipe_block1)

[0129] df['pipe_block2'] = df.apply(pipe_block2)

[0130] df['pipe_block3'] = df.apply(pipe_block3)

[0131] A specific embodiment of the data processing method of the soft test point in the industrial system provided by the embodiment of the present invention is:

[0132] The system dynamics model of the generator wire rod water cooling system is as follows: Figure 2 As shown, the working mechanism of the system is: the electric water pump drives the cooling water circulation to perform heat exchange and cooling on the generator wire rods. The cooling water pipe may be blocked for various reasons, affecting the cooling effect. Therefore, it is necessary to monitor the working status of the measuring point whose indicator data is the cooling water flow rate, so that the cooling water pipe can be handled in time when it is blocked. However, the measuring points whose indicator data are cooling water flow rate and water resistance are all unmeasurable points. The embodiment of the present invention obtains the indicator data of the unmeasurable point through the following process, which specifically includes:

[0133] Step 1: According to the system dynamics model of the generator wire rod water cooling system, determine the relationship map of each measuring point and obtain the extended system dynamics model, such as Figure 2~3 As shown, where measuring point A 1 , A 2 , A 3 , A 4 , A 5 , A 6 and A 7The corresponding indicator data are cooling water flow rate, cooling water pipe cross-sectional area, cooling water pipe pressure difference, cooling water pipe narrow cross-sectional area, cooling water flow, water resistance and wire rod temperature, which are recorded as indicator variables x 1 、x 2 、x 3 、x 4 、x 5 、x 6 and x 7 ,

[0134] With unmeasurable point A 5 The measurement points with associated relationships include A 1 , A 2 , A 3 , A 4 , A 6 and A 7 ; and unmeasurable point A 6 The measurement points with associated relationships include A 5 .

[0135] Step 2: Determine the impact grouping of the target unmeasurable point data according to the extended system dynamics model and the impact relationship between the measurable point and the target unmeasurable point. The specific implementation process includes:

[0136] According to the velocity area calculation method, the cooling water flow rate can be calculated by the cooling water velocity and the cooling water pipe cross-sectional area. The calculation expression is: 5 =f(x 1 , x 2 ); where f is the velocity area calculation function;

[0137] According to the differential pressure calculation method, the cooling water flow rate can also be calculated through the pressure difference of the cooling water pipe and the cross-sectional area of ​​the narrow part of the cooling water pipe. The calculation expression is expressed as: 5 =g(x 3 , x 4 ); where g is the differential pressure calculation function;

[0138] Under the premise of constant pump power, there is a monotonic relationship between cooling water flow and water resistance, which can be expressed as: 6 =h -1 (x 5 ), or x 5 =h(x 6 ); where h is a calculation function, which can be obtained by fitting based on the experimental results of the test machine;

[0139] Under the premise of constant cooling water temperature, there is a monotonic relationship between cooling water flow and wire rod temperature, which can be expressed as: 5 =t(x 7 ), or x 7=t -1 (x 5 ); where t is the calculation function, obtained through experimental fitting;

[0140] It can be obtained that for the unmeasurable point "cooling water flow", there are 4 impact groups, namely { A 1 , A 2}, { A 3 , A 4}、{A 6}, { A 7}.

[0141] Step 3, according to the impact group of the target unmeasurable point data, determine the measurement point calculation relationship map;

[0142] The specific implementation process includes: determining the measurement point calculation relationship map (i.e., path set) according to the impact grouping of the target unmeasurable point data, the operation relationship between the measurement points, and the monotonicity of the function. The measurement point calculation relationship map includes multiple sub-graphs, such as Figures 4 to 7 As shown, each subgraph includes multiple measurement points and the topological relationships of multiple measurement points. If there are n monotonic functions, the number of subgraphs is 2. n .

[0143] Step 4: According to the measurement point calculation relationship map, traverse all calculation paths, and the calculation paths of the unmeasurable points "cooling water flow" and "water resistance" are obtained as follows:

[0144] x 5 =f(x 1 , x 2 ) or x 5 =g(x 3 , x 4 ) or x 5 =t(x 7 );

[0145] x 6 =h -1 (x 5 )=h -1 [f(x 1 , x 2 )] or x 6 =h -1 (x 5 )=h -1 [g(x 3 , x 4 )] or x 6 =h -1 (x 5 ) = h[t(x 7 )].

[0146] Step 5, unmeasurable point A5 and A 6 The number of calculation paths is 3, so point A cannot be measured. 5 and A 6 All are computable measuring points. The calculation results of each calculation path are output in turn to obtain the unmeasurable point A. 5 The result set R 5 and A 6 The result set R 6 .

[0147] Step 6: For the result set R 5 or R 6 Perform difference detection to obtain the index data of the target unmeasurable point and use the result set R 5 Take the example, the specific process includes: calculating the target unmeasurable point result set R 5 The mean and standard deviation of the calculation paths are compared with the preset value. When the standard deviation is less than the preset value, it means that the calculation results of each calculation path are slightly different, and the mean value can be used as the indicator data of the target unmeasurable point. When the standard deviation is greater than or equal to the preset value, it means that the calculation results of each calculation path are quite different, and the result set R is selected. 5 The calculation result with the largest difference from the mean is excluded, the mean and standard deviation of the result set are recalculated and the above detection process is repeated until the standard deviation is less than the preset value, and the mean at this time is used as the indicator data of the target unmeasurable point.

[0148] The data processing method of soft measuring points in industrial systems proposed by the present invention can provide users with transparent access to "soft measurements", obtain parameters of unmeasurable points like accessing basic measuring points, perform reasoning through measuring point calculation graphs, obtain index data of unmeasurable points, and automatically interpret and execute measuring points, read measurable measuring points (raw data) from a database and convert them into soft measurements; in the case where a soft measurement has multiple calculation methods, automatically analyze whether there is a result that significantly deviates from other results, and output the final result after detection, thereby improving the output efficiency of data of unmeasurable points.

[0149] like Fig.10 As shown, an embodiment of the present invention provides a data processing device 10 for soft test points in an industrial system, and the data processing device 10 includes:

[0150] The modeling module 101 is used to obtain the target unmeasurable point data and the influence relationship by extending the system dynamics model; wherein the extended system dynamics model includes: the influence grouping of the target unmeasurable point data, and the function calculation relationship and the monotonicity of the function between multiple measurable points and the unmeasurable points in the influence grouping; the influence grouping includes multiple measurable points, and the multiple measurable points have an influence relationship with the target unmeasurable point, and the influences of different influence groups on the target unmeasurable point are independent of each other;

[0151] A reasoning module 102, configured to derive a calculation method for target unmeasurable points according to the extended system dynamics model;

[0152] A query module 103, used to automatically perform calculations according to the calculation method of the target unmeasurable point and respond to user queries;

[0153] The anomaly detection module 104 is used to perform distribution statistics on the multiple result sets when there are multiple result sets for the target unmeasurable point, so as to realize abnormal outlier result set detection.

[0154] Optionally, the modeling module 101 may include:

[0155] According to the extended system dynamics model, target unmeasurable point data of the extended system dynamics model are determined; wherein the target unmeasurable point data include indicator variables of the target unmeasurable point and mechanism influence relationships between the target unmeasurable point and other measurement point variables in the extended system dynamics model.

[0156] Optionally, the impact grouping of the target unmeasurable point data includes:

[0157] A plurality of measurable points associated with the target unmeasurable point, and a plurality of operation expressions obtained according to association relationships between the indicator variables corresponding to the target unmeasurable point and the plurality of indicator variables corresponding to the associated plurality of measurable points;

[0158] Among them, the indicator variable corresponding to the target unmeasurable point is the dependent variable of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; the multiple measurable points corresponding to the independent variables in an operation expression constitute an influence group.

[0159] Optionally, the reasoning module 102 may include:

[0160] Determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model;

[0161] Combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression;

[0162] According to the calculation path, a calculation method for the target unmeasurable point is obtained.

[0163] Optionally, all associated measuring points of the target unmeasurable point are combined according to the impact grouping to obtain a calculation path, including:

[0164] In the extended system dynamics model, starting from the location of the target unmeasurable point, all associated measuring points of the target unmeasurable point are traversed in sequence, and combined according to the impact grouping to obtain a measuring point set V tree And the topological relationship set L between the measuring points tree ;

[0165] According to the measuring point set V tree and the topological relationship set L tree , and sequentially construct the path set L between the target unmeasurable point and each measuring point, L={V tree ∪L tree};

[0166] According to the path set L, a calculation path is obtained.

[0167] Optionally, the query module 103 may include:

[0168] Determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable;

[0169] If the target unmeasurable point can be calculated, the calculation results of each calculation path are output in turn to obtain multiple result sets R of the target unmeasurable point;

[0170] Output multiple result sets R of the target unmeasurable points to respond to user queries.

[0171] Optionally, the anomaly detection module 104 may include:

[0172] Calculate the mean and standard deviation of multiple result sets R of the target unmeasurable point;

[0173] Comparing the standard deviation with a first preset value to obtain a comparison result;

[0174] According to the comparison result, the index data of the target unmeasurable point is obtained.

[0175] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0176] like Fig.11 As shown, the embodiment of the present invention further provides a computing device 11, including a processor 111, a memory 112, a program or instruction stored in the memory 112 and executable on the processor 111, and when the program or instruction is executed by the processor 111, each process of the data processing method of the soft test point in the above industrial system is implemented, and the same technical effect can be achieved. To avoid repetition, it is not described here. It should be noted that the computing device in the embodiment of the present invention includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0177] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0179] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0180] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0182] Stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or optical disk, etc., various media that can store program codes.

[0183] In addition, it should be pointed out that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understandable that all or any steps or components of the method and apparatus of the present invention can be implemented in hardware, firmware, software or a combination thereof in any computing device (including processors, storage media, etc.) or a network of computing devices, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0184] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code for implementing a method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0185] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A data processing method for soft measurement points in an industrial system, It is characterized in that include: Receive a query request for target unmeasurable point data of an industrial system dynamics model; The query request carries: the index data to be outputted of the target unmeasurable point; the index data of multiple measurable points stored in the basic measuring point time series database; The target unmeasurable point data and influence relationship are obtained by extending the system dynamics model; wherein the extended system dynamics model includes: the influence grouping of the target unmeasurable point data, and the function calculation relationship and the monotonicity of the function between multiple measurable points and unmeasurable points in the influence grouping, and the relationship map of the network structure formed between the unmeasurable points and the measurable points; the influence grouping includes multiple measurable points, and the multiple measurable points have influence relationships with the target unmeasurable points, and the influences of different influence groups on the target unmeasurable points are independent of each other; According to the extended system dynamics model, a calculation method of the target unmeasurable point is derived; Automatically perform calculations according to the calculation method of the target unmeasurable point and respond to user queries; When there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to achieve abnormal outlier result set detection; The method of obtaining target unmeasurable point data and influence relationships by expanding the system dynamics model includes: According to the system dynamics model of the generator wire rod water cooling system, the relationship map of each measuring point is determined to obtain the extended system dynamics model, and the target unmeasurable point data of the extended system dynamics model is determined; wherein the target unmeasurable point data includes the indicator variable of the target unmeasurable point and the mechanism influence relationship between the target unmeasurable point and other measuring point variables in the extended system dynamics model; The impact grouping of the target unmeasurable point data includes: A plurality of measurable points associated with the target unmeasurable point, and a plurality of operation expressions obtained according to association relationships between the indicator variables corresponding to the target unmeasurable point and the plurality of indicator variables corresponding to the associated plurality of measurable points; The indicator variables corresponding to the target unmeasurable points are the dependent variables of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; the multiple measurable points corresponding to the independent variables in one operation expression constitute an impact group; Among them, the cooling water flow rate is calculated by the cooling water flow rate and the cooling water pipe cross-sectional area, and its operation expression is expressed as: 5 =f(x 1 , x 2 ), where f is the velocity area calculation function; The cooling water flow rate is calculated by the cooling water pipe pressure difference and the cross-sectional area of ​​the cooling water pipe narrow part. The calculation expression is: 5 =g(x 3 , x 4 ), where g is the differential pressure calculation function; When the pump power is constant, the cooling water flow rate and water resistance are monotonically related, expressed as: 6 =h -1 (x 5 ), or x 5 =h(x 6 ), where h is the calculation function; When the cooling water temperature is constant, there is a monotonic relationship between the cooling water flow rate and the wire rod temperature, which can be expressed as: 5 =t(x 7 ), or x 7 =t -1 (x 5 ), where t is the calculation function; For the unmeasurable point "cooling water flow", there are 4 impact groups, namely {A 1 , A 2 }、{A 3 , A 4 }、{A 6 }、{A 7 }, where A 1 , A 2 , A 3 , A 4 , A 6 and A 7 The corresponding index data are cooling water flow rate, cooling water pipe cross-sectional area, cooling water pipe pressure difference, cooling water pipe narrow cross-sectional area, water resistance and wire rod temperature; Wherein, according to the extended system dynamics model, a calculation method for deriving the target unmeasurable point includes: Determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model; Combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression; According to the calculation path, a calculation method for obtaining the target unmeasurable point is obtained; The step of combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path includes: In the extended system dynamics model, starting from the location of the target unmeasurable point, all associated measuring points of the target unmeasurable point are traversed in sequence, and combined according to the impact grouping to obtain a measuring point set V tree And the topological relationship set L between the measuring points tree , wherein the location of the target unmeasurable point is determined by the relationship map; According to the measuring point set V tree and the topological relationship set L tree , where L tree Contains the influence grouping data of the measuring points and the monotonicity data of the operation function, and sequentially constructs the path set L between the target unmeasurable point and each measuring point, L = {V tree ∪L tree }; According to the path set L, all operation expressions of the target unmeasurable points are obtained, and the relationship graph is divided into multiple subgraphs, each of which includes multiple measurement points and the topological relationships of the multiple measurement points. When the number of monotonic functions is n, the number of subgraphs is 2 n ,According to each calculation path, the calculation method of the target unmeasurable point is obtained; Wherein, automatically calculating according to the calculation method of the target unmeasurable point and responding to user queries include: Determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable; If the target unmeasurable point can be calculated, the calculation results of each calculation path are output in turn to obtain multiple result sets R of the target unmeasurable point; Output multiple result sets R of the target unmeasurable points to respond to user queries.

2. The data processing method of soft measuring points in an industrial system according to claim 1, It is characterized in that When there are multiple result sets for the target unmeasurable point, distribution statistics are performed on the multiple result sets to implement abnormal outlier result set detection, including: Calculate the mean and standard deviation of multiple result sets R of the target unmeasurable point; Comparing the standard deviation with a first preset value to obtain a comparison result; According to the comparison result, the index data of the target unmeasurable point is obtained.

3. A data processing device for soft measurement points in an industrial system, It is characterized in that The processing device comprises: A modeling module is used to receive a query request for target unmeasurable point data of an industrial system dynamics model; the query request carries: the index data to be output of the target unmeasurable point; the index data of multiple measurable points are stored in a basic measurement point time series database; the target unmeasurable point data and influence relationship are obtained by extending the system dynamics model; wherein the extended system dynamics model includes: the influence grouping of the target unmeasurable point data, and the function calculation relationship and the monotonicity of the function between multiple measurable points and unmeasurable points in the influence grouping, and a relationship map of a mesh structure formed between unmeasurable points and measurable points; the influence grouping includes multiple measurable points, and the multiple measurable points have an influence relationship with the target unmeasurable point, and the influences of different influence groups on the target unmeasurable point are independent of each other; A reasoning module, used for deriving a calculation method of a target unmeasurable point according to the extended system dynamics model; A query module, used to automatically perform calculations according to the calculation method of the target unmeasurable points and respond to user queries; An anomaly detection module, used for performing distribution statistics on the multiple result sets when there are multiple result sets for the target unmeasurable point, so as to realize abnormal outlier result set detection; The method of obtaining target unmeasurable point data and influence relationships by expanding the system dynamics model includes: According to the extended system dynamics model, determining target unmeasurable point data of the extended system dynamics model; wherein the target unmeasurable point data includes an indicator variable of the target unmeasurable point and a mechanism influence relationship between the target unmeasurable point and other measurement point variables in the extended system dynamics model; The impact grouping of the target unmeasurable point data includes: A plurality of measurable points associated with the target unmeasurable point, and a plurality of operation expressions obtained according to association relationships between the indicator variables corresponding to the target unmeasurable point and the plurality of indicator variables corresponding to the associated plurality of measurable points; The indicator variables corresponding to the target unmeasurable points are the dependent variables of the multiple operation expressions, and the multiple indicator variables corresponding to the associated multiple measurable points are the independent variables of the multiple operation expressions; the multiple measurable points corresponding to the independent variables in one operation expression constitute an impact group; Among them, the cooling water flow rate is calculated by the cooling water flow rate and the cooling water pipe cross-sectional area, and its operation expression is expressed as: 5 =f(x 1 , x 2 ), where f is the velocity area calculation function; The cooling water flow rate is calculated by the cooling water pipe pressure difference and the cross-sectional area of ​​the cooling water pipe narrow part. The calculation expression is: 5 =g(x 3 , x 4 ), where g is the differential pressure calculation function; When the pump power is constant, the cooling water flow rate and water resistance are monotonically related, expressed as: 6 =h -1 (x 5 ), or x 5 =h(x 6 ), where h is the calculation function; When the cooling water temperature is constant, there is a monotonic relationship between the cooling water flow rate and the wire rod temperature, which can be expressed as: 5 =t(x 7 ), or x 7 =t -1 (x 5 ), where t is the calculation function; For the unmeasurable point "cooling water flow", there are 4 impact groups, namely {A 1 , A 2 }、{A 3 , A 4 }、{A 6 }、{A 7 }, where A 1 , A 2 , A 3 , A 4 , A 6 and A 7 The corresponding index data are cooling water flow rate, cooling water pipe cross-sectional area, cooling water pipe pressure difference, cooling water pipe narrow cross-sectional area, water resistance and wire rod temperature; Wherein, according to the extended system dynamics model, a calculation method for deriving the target unmeasurable point includes: Determining all associated measuring points of the target unmeasurable point according to the extended system dynamics model; Combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path; wherein one calculation path corresponds to one operation expression; According to the calculation path, a calculation method for obtaining the target unmeasurable point is obtained; The step of combining all associated measuring points of the target unmeasurable point according to the impact grouping to obtain a calculation path includes: In the extended system dynamics model, starting from the location of the target unmeasurable point, all associated measuring points of the target unmeasurable point are traversed in sequence, and combined according to the impact grouping to obtain a measuring point set V tree And the topological relationship set L between the measuring points tree , wherein the location of the target unmeasurable point is determined by the relationship map; According to the measuring point set V tree and the topological relationship set L tree , where L tree Contains the influence grouping data of the measuring points and the monotonicity data of the operation function, and sequentially constructs the path set L between the target unmeasurable point and each measuring point, L = {V tree ∪L tree }; According to the path set L, all operation expressions of the target unmeasurable points are obtained, and the relationship graph is divided into multiple subgraphs, each of which includes multiple measurement points and the topological relationships of the multiple measurement points. When the number of monotonic functions is n, the number of subgraphs is 2 n ,According to each calculation path, the calculation method of the target unmeasurable point is obtained; Wherein, automatically calculating according to the calculation method of the target unmeasurable point and responding to user queries include: Determining whether the target unmeasurable point is computable according to the calculation path; wherein, when the number of the calculation paths is zero, the target unmeasurable point is not computable; If the target unmeasurable point can be calculated, the calculation results of each calculation path are output in turn to obtain multiple result sets R of the target unmeasurable point; Output multiple result sets R of the target unmeasurable points to respond to user queries.

4. A computing device, It is characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 2 is performed.

5. A computer-readable storage medium, It is characterized in that Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 2.

Citation Information

Patent Citations

  • Cobalt oxalate coarseness prediction technique in hydrometallurgy synthesis course

    CN101482750A

  • Monte Carlo cross verification-based multiple-soft sensing algorithm cluster modeling method

    CN106897774A

  • Variable prediction method, device and equipment for system dynamics model of industrial equipment

    CN115048826A

  • Sewage treatment-oriented photosynthetic bacteria fermentation process soft measurement method

    CN115579063A

  • Vehicle operation monitoring, overseeing, data processing and overload monitoring method and system

    US20170309093A1