A plant intelligent function evaluation method and system

Abstract

The application provides a plant intelligent function evaluation method and system, the method comprises the following steps: according to the plant physical operation logic and user measuring point demand analysis, analyzing the required measuring point information corresponding to the plant intelligent function, and calculating the feasibility weight coefficient of the measuring point relative to the intelligent function; collecting all measuring point information of the target plant, screening the measuring points meeting the requirements, and evaluating the overall quality of the measuring points meeting the requirements; inputting the feasibility weight importance coefficient of the measuring point relative to the intelligent function and the overall quality of the measuring point into the intelligent function evaluation model to evaluate each required intelligent function. The advantage of the application lies in that the plant intelligent transformation feasibility evaluation method provided by the application provides a guidance standard for scientifically evaluating whether the plant side measuring point conditions meet the conditions for constructing intelligent functions such as fault diagnosis, fault warning, operation optimization; the plant intelligent transformation cost can be saved, and the intelligent transformation reference for the user can be provided in advance.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of intelligent control of air cooling systems of coal-fired power plants, and particularly relates to a method and system for evaluating intelligent functions of a plant. BACKGROUND

[0002] In the current increasing number of cases of digital transformation of plants, plant-side measurement point data information, as the basis for digital transformation, is a prerequisite for digital transformation. However, according to the current research, there is no mature system or model that can scientifically evaluate whether the measurement point conditions of plant digital transformation are mature. The main reasons are: 1. Due to the rapid development of digital transformation of traditional industries including air cooling systems of coal-fired power plants, the technology is advancing rapidly, and the detection methods are diversified. There is no complete and scientific industry digital transformation standard; 2. The requirements of plant digital transformation measurement points will change according to user needs, and the degree of digitalization and intelligence and requirements are different; 3. The plant environment is different, and the layout, environmental conditions, and measurement point conditions of different plants are different. It is difficult to evaluate with a unified standard; 4. The sensor arrangement and measurement point accuracy are different in each process production link of the plant side. The cost is high when some technical means are used to complete the digital and intelligent transformation requirements, and the evaluation of measurement point conditions cannot be mature and reasonable.

[0003] The main references of the present application are "An intelligent evaluation system for power distribution network engineering cost", "Intelligent project evaluation collaborative management system", and "Highly reliable power system transient stability intelligent evaluation system and method". It is feasible to upgrade and transform the intelligent technology of traditional industries combined with deep learning algorithm. LSTM is a variant model of recurrent neural network RNN. It solves the problems of gradient disappearance and gradient explosion, insufficient long-term memory capacity, and other problems of RNN, so that the recurrent neural network can truly and effectively utilize long-distance time sequence information. LSTM network has been proven to be more effective than traditional RNN. LSTM has been widely used and has excellent performance in data prediction. The main problems of the current existing technology are: 1. With the increasing demand for digital and intelligent transformation of traditional industries, how to scientifically evaluate whether the plant-side measurement point conditions meet the requirements of intelligent functions such as fault diagnosis, fault warning, and operation optimization; 2. The evaluation efficiency is low and the labor cost is high through traditional means using artificial experience; 3. The confidence of the classifier or neural network learning method based on various ensemble learning models is low, and it cannot meet the current actual transformation needs of users and plant sides. SUMMARY

[0004] The purpose of the present application is to overcome the defects of the prior art that cannot meet the plant digital transformation requirements for measurement point evaluation, which is difficult and costly, and there is no unified standard.

[0005] In order to achieve the above object, the present application provides a plant intelligent function evaluation method, which comprises the following steps:

[0006] Step 1: According to the physical operation logic of the plant and the user measurement point demand analysis, the required measurement point information corresponding to the intelligent function of the plant is analyzed, and the feasibility weighted importance coefficient of the measurement point relative to the intelligent function is calculated;

[0007] Step 2: Collect all measurement point information of the target plant, screen the measurement points meeting the requirements, and evaluate the overall quality of the measurement points meeting the requirements;

[0008] Step 3: The feasibility weighted importance coefficient of the measurement point relative to the intelligent function and the overall quality of the measurement point are input into the intelligent function evaluation model to evaluate each required intelligent function.

[0009] As an improvement of the above method, the step 1 specifically comprises:

[0010] Step 1-1: The user's intelligent function demand is analyzed and decomposed, the production link of the plant corresponding to the demand is confirmed, and the measurement point information required by the demand for each production link is determined;

[0011] Step 1-2: The physical logic analysis of the plant intelligent transformation demand required by the user is performed, and the main variable measurement point of each intelligent function is determined according to the physical logic;

[0012] Step 1-3: The main variable measurement point importance coefficient corresponding to the intelligent function is determined as 1, and the correlation of other measurement points to the main variable of the intelligent function is analyzed, which is used as the weighted importance coefficient of the feasibility of each measurement point to the intelligent function.

[0013] As an improvement of the above method, the formula for calculating the feasibility weighted importance coefficient is:

[0014]

[0015] Wherein, ω represents the feasibility weighted importance coefficient of the to-be-evaluated measurement point relative to an intelligent function; n represents the total number of samples, i.e. the number of measurement data of the to-be-evaluated measurement point within a period of time; x i is the i-th data measured within a period of time by the main variable measurement point corresponding to the intelligent function of the to-be-evaluated measurement point, i.e. factor 1; y i is the i-th data measured within a period of time by the to-be-evaluated measurement point, i.e. factor 2; is the average value of factor 1; is the average value of factor 2.

[0016] As an improvement of the above method, the step 2 specifically comprises:

[0017] Step 2-1: read all the information of the measuring points in the factory building, judge the accuracy and completeness of the measuring points according to the measuring point situation, and screen the measuring points meeting the requirements; the accuracy refers to the degree of coincidence between the data obtained by the measuring point and the actual situation; the completeness refers to the interval of the data obtained by the measuring point meeting the demand of intelligent function;

[0018] Step 2-2: evaluate the overall quality of the measuring points meeting the requirements.

[0019] As an improvement of the above method, the overall quality evaluation formula of the measuring points is:

[0020]

[0021] Wherein, λ' represents the historical time sequence quality coefficient of the measuring point; normal working condition point represents the number of normal measurement data in a period of historical data; abnormal working condition point represents the number of abnormal measurement data in a period of historical data.

[0022] As an improvement of the above method, the step 3 specifically comprises:

[0023] Step 3-1: taking the quality coefficient of each measuring point as the target variable, taking the historical measurement data of the measuring point time sequence and the historical time sequence quality coefficient of each measuring point calculated in step 2 as the independent variable input, inputting the neural network model, and predicting the quality coefficient value of the specified time sequence of each measuring point as the quality coefficient of the measuring point;

[0024] Step 3-2: according to the weight coefficient ω of the feasibility of each intelligent function corresponding to each measuring point and the quality coefficient λ of each measuring point, the feasibility of each intelligent function is analyzed and evaluated.

[0025] As an improvement of the above method, the intelligent function evaluation model is:

[0026]

[0027] Wherein, T m represents the result of the intelligent function evaluation of the mth intelligent function on the k measuring points, and the range is 0-1; ω im represents the feasibility weighted importance coefficient of the ith measuring point to the mth intelligent function; λ j represents the quality coefficient of the jth measuring point;

[0028] According to the requirements of each intelligent function, the threshold value K of each intelligent function is set, and the evaluation result exceeding the threshold value K represents that the intelligent function evaluation result meets the standard, that is, the condition of intelligent function upgrading and reconstruction is met.

[0029] The application also provides a factory building intelligent function evaluation system, the system comprises:

[0030] A feasibility weight coefficient module is configured to analyze the required measuring point information corresponding to the intelligent function of the factory building according to the physical operation logic of the factory building and the user measuring point demand analysis, and calculate the feasibility weight coefficient of the measuring point relative to the intelligent function.

[0031] An overall quality condition evaluation module is configured to collect all measuring point information of the target factory building, screen the measuring points meeting the requirements, and evaluate the overall quality condition of the measuring points meeting the requirements.

[0032] An intelligent function evaluation module is configured to input the feasibility weighted importance coefficient of the measuring point relative to the intelligent function and the overall quality condition of the measuring point into an intelligent function evaluation model to evaluate each required intelligent function.

[0033] The application further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method according to any one of the above when executing the computer program.

[0034] The application further provides a computer readable storage medium, which stores a computer program, and the computer program makes the processor execute the method according to any one of the above when being executed by the processor.

[0035] Compared with the prior art, the application has the following advantages:

[0036] The factory building intelligent transformation feasibility evaluation method provided by the application provides a guidance standard for scientifically evaluating whether the factory building measuring point condition meets the condition of constructing intelligent functions such as fault diagnosis, fault early warning, and operation optimization, can save the intelligent transformation cost of the factory building, and provides a reference for intelligent transformation for users in advance. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 Fig. 1 shows a flowchart of a factory building intelligent function evaluation method and system;

[0038] Figure 2 Fig. 3 shows an evaluation principle diagram of an intelligent function evaluation model;

[0039] Figure 3 Fig. 4 shows a flowchart of an intelligent function evaluation model evaluation process;

[0040] Figure 4 Fig. 5 shows an evaluation result transmission diagram;

[0041] Figure 5 Fig. 6 shows a schematic diagram of an LSTM neural network principle. DETAILED DESCRIPTION

[0042] The technical solutions of the application will be described in detail below with reference to the drawings.

[0043] For the intelligent function evaluation of factory building, an intelligent function evaluation method and system for factory building are provided to solve the problems that 1. with the increasing demand for the digitalization and intelligent transformation of traditional industry, how to scientifically evaluate whether the factory side measurement point condition has the condition for constructing intelligent functions such as fault diagnosis, fault warning, operation optimization, etc.; 2. the problems that the evaluation efficiency is low and the labor cost is high by using traditional manual experience method; 3. the problems that the confidence of the method of constructing classifier or neural network learning based on various integrated learning models is low, and cannot meet the current actual transformation demand of users and factory side.

[0044] As shown in Figure 1 , Figure 2 Embodiment 1 of the present application provides an intelligent function evaluation method for factory building, which comprises the following steps:

[0045] S1: According to the physical operation logic of the factory building and the user measurement point demand analysis, the user side required measurement point information corresponding to the intelligent function of the factory building is analyzed, the feasibility weighted importance coefficient of the measurement point relative to the intelligent function is calculated, and an intelligent function evaluation model is established;

[0046] S11: User demand analysis, the user required intelligent function demand is analyzed and decomposed, and the modules of each demand corresponding to the factory building are confirmed; (for example of coal-fired power plant air cooling island: 1. intelligent early warning function, the module link required to be transformed includes: air cooling island fan group side, radiator pipe bundle side; 2. fault diagnosis function, the module link required to be transformed includes: air cooling island fan group side; 3. operation optimization function, the link required to be transformed includes: air cooling island fan group side, boiler turbine side, air cooling island electrical side, environment side).

[0047] The intelligent function demand includes but is not limited to intelligent early warning function, fault diagnosis function, operation optimization function, unattended, intelligent inspection, intelligent report and other intelligent transformation demands.

[0048] S12: Importance evaluation, the physical logic analysis of the intelligent transformation demand of the factory building required by the user is carried out, the measurement point information required by the user for each production link is determined, and the main variable measurement point of each intelligent function is determined according to the physical logic. The main variable is the physical property mainly concerned by the intelligent function, such as temperature, vibration amplitude, etc.; the main variable measurement point is the measurement point information essential for measuring the main variable of the intelligent function.

[0049] Firstly, the main variable measuring point corresponding to the intelligent function main variable is determined, the measuring point importance coefficient is determined as 1, then Pearson correlation analysis is used to analyze the correlation of other measuring points to the intelligent function main variable, which is used as the weighted importance coefficient of the measuring points to the intelligent function feasibility.

[0050] S13: Establish an intelligent function evaluation model, and the weight coefficient of each measuring point to the feasibility of each intelligent function is obtained through S12, and an intelligent function evaluation model is established.

[0051] The intelligent evaluation model is a comprehensive model combining a mathematical model and an LSTM long short-term memory artificial neural network, wherein the main variable measuring point corresponding to each intelligent function is obtained by analyzing the physical mechanism, and then the feasibility weight coefficient ω of each measuring point corresponding to different intelligent functions is obtained through Pearson correlation coefficient analysis, and the Pearson calculation formula is as follows:

[0052]

[0053] Wherein, ρ represents the Pearson correlation coefficient, that is, the feasibility weighted importance coefficient ω of the to-be-evaluated measuring point relative to an intelligent function; n represents the total number of samples, that is, the number of measuring data of the to-be-evaluated measuring point within a period of time; x i is factor 1, that is, the i-th data of the main variable measuring point corresponding to the intelligent function of the to-be-evaluated measuring point measured within a period of time; y i is factor 2, that is, the i-th data of the to-be-evaluated measuring point measured within a period of time; is the average value of factor 1; is the average value of factor 2.

[0054] S2: Collect all measuring point information of the target plant, judge the accuracy and completeness of the measuring points according to the measuring point situation, and select the measuring points meeting the requirements;

[0055] S21: Read all related process link measuring point information of the plant side;

[0056] In one implementation process of the present application, the full-plant measuring point information of the coal-fired power plant is queried and accessed through the SIS system.

[0057] For example Figure 3As shown, the access system point information needs to judge whether the point data meets the requirements of intelligent function, including accuracy and completeness. Accuracy refers to the degree of consistency between the data obtained by the point and the actual situation; completeness refers to the interval of the data obtained by the point meeting the requirements of intelligent function; for example, judging whether the data precision and data interval (1s, 2s, 30s, 60s, etc.) meet the requirements of intelligent function. Only collect the point information that meets the requirements.

[0058] S22: According to the completeness of the point data and the accuracy of each point sensor, it is judged whether the point data meets the requirements of the point, and the overall quality of each point is evaluated;

[0059] The overall quality of each point is evaluated, first, the historical data of each intelligent function required point is collected, the historical data time sequence range is specified, and the quality coefficient λ of each point is calculated by using the historical data of the specified time sequence range, the value range is 0-1, and the calculation formula is as follows:

[0060]

[0061] S23: Collect the point information that meets the requirements.

[0062] S3: Input all the required point information in the target plant into the intelligent function evaluation model to evaluate each required intelligent function;

[0063] S31: Input all the required points into the intelligent function evaluation model;

[0064] The weight coefficient of point k for intelligent function 1, intelligent function 2, and intelligent function n calculated by Pearson is ω k1 , ω k2 , and ω kn , respectively, and the value range of the weight coefficient ω is 0-1;

[0065] As shown in Figure 5 , the quality coefficient λ of each point is taken as the target variable, and the time sequence historical data of the point related parameters and the historical time sequence quality coefficient λ of each point calculated in step S22 are taken as the independent variables, an LSTM long short-term memory artificial neural network model is established, and the λ quality coefficient value of each point at a specified time sequence is predicted as the quality coefficient λ of the point.

[0066] The intelligent function evaluation model evaluation calculation method, by calculating the quality coefficient λ of each point and the weight coefficient ω of each point corresponding to each intelligent function, respectively, the feasibility of each intelligent function is evaluated by using the following formula:

[0067]

[0068] Tn represents the result of the nth intelligent function evaluating the k measuring points, ranging from 0 to 1; ω in ω represents the weighted importance coefficient of the ith measuring point to the nth intelligent function; λ i λ represents the quality coefficient of the ith measuring point; the threshold K can be set according to the requirements of each intelligent function, and the threshold K is exceeded, which means that the intelligent function evaluation result meets the standard, that is, the condition for upgrading the intelligent function;

[0069] S32: according to the weight coefficient ω of each measuring point to the feasibility of each intelligent function and the quality coefficient λ of each measuring point, the feasibility of each intelligent function is analyzed and evaluated, and the evaluation result (report) is output and displayed, as shown in Figure 4

[0070] The evaluation result of the intelligent function evaluation model needs to be displayed through an automatic report generation module or a visual interface to show the influence of each measuring point on the evaluation result.

[0071] S4: the intelligent function model evaluation result is transmitted to the user side and the plant side.

[0072] S41: the intelligent function model evaluation result is transmitted to the user side, and the user side judges according to the intelligent function feasibility evaluation result;

[0073] S42: the intelligent function model evaluation result is transmitted to the plant side, and the plant side is modified according to the intelligent function feasibility evaluation result.

[0074] Embodiment 2 of the present application provides a plant intelligent function evaluation system, which comprises:

[0075] The feasibility weight coefficient module is used for analyzing the plant intelligent function corresponding to the required measuring point information according to the plant physical operation logic and user measuring point demand analysis, and calculating the feasibility weight coefficient of the measuring point relative to the intelligent function;

[0076] The overall quality condition evaluation module is used for collecting all measuring point information of the target plant, screening the measuring points meeting the requirements, and evaluating the overall quality condition of the measuring points meeting the requirements; and

[0077] The intelligent function evaluation module is used for inputting all required measuring point information in the target plant into the intelligent function evaluation model to evaluate each required intelligent function.

[0078] The present application is an effective evaluation method for the intelligent transformation feasibility of a plant (especially a coal-fired power plant air cooling island) based on user demand;

[0079] ​The present application is directed to a plant (especially a coal-fired power plant air cooling island) intelligent function feasibility evaluation comprehensive model, which calculates the quality coefficient lambda and the weight coefficient omega by using an LSTM neural network and Pearson correlation calculation, respectively.

[0080] The present application is a practical evaluation method based on the overall quality lambda of the measuring points and the weight coefficient omega of each measuring point to each intelligent function requirement.

[0081] The plant intelligent transformation feasibility evaluation method provided by the present application provides certain guidance standards for scientifically evaluating whether the plant measuring point conditions meet the conditions for constructing intelligent functions such as fault diagnosis, fault early warning, and operation optimization; can save the intelligent transformation cost of the plant (especially the coal-fired power plant air cooling island), and provide intelligent transformation reference for users in advance.

[0082] The present application can also provide a computer device, which includes at least one processor, memory, at least one network interface and user interface. The various components in the device are coupled together through a bus system. It can be understood that the bus system is used to realize the connection and communication between the components. In addition to the data bus, the bus system also includes power supply bus, control bus and state signal bus.

[0083] The user interface can include a display, a keyboard or a clicking device (for example, a mouse, a trackball, a touchpad or a touch screen, etc.).

[0084] It is to be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory described herein is intended to include, without being limited to, these and any other suitable types of memory.

[0085] In some embodiments, the memory stores elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system and an application program.

[0086] Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application program includes various application programs, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The program for implementing the method of the embodiments of the present disclosure can be included in the application program.

[0087] In the above-mentioned embodiments, the processor can also be used to execute the steps of the above-mentioned method by invoking the program or instructions stored in the memory, in particular, the program or instructions stored in the application program.

[0088] execute the steps of the above-mentioned method.

[0089] The method can be applied to a processor or implemented by the processor. The processor can be an integrated circuit chip having a signal processing capability. In implementation, the steps of the method can be completed by an integrated logic circuit of hardware in the processor or by an instruction in the form of software. The processor can be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods disclosed above can be implemented or executed by the processor. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed above can be directly embodied as a hardware code executed by the processor or a combination of hardware and software modules in the processor. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage media is located in the storage memory, and the processor reads information in the storage memory and combines the hardware to complete the steps of the method.

[0090] It can be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units can be implemented within one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSP Devices), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.

[0091] For a software implementation, the techniques can be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes can be stored in memory and executed by processors. The memory can be implemented within the processor or external to the processor.

[0092] The application further provides a nonvolatile storage medium for storing the computer program. When the computer program is executed by a processor, each step in the above method embodiment can be implemented.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A plant intelligent function evaluation method, the method comprising: Step 1: analyzing the required measuring point information corresponding to the plant intelligent function according to the plant physical operation logic and user measuring point demand analysis, and calculating the feasibility weighted importance coefficient of the measuring point relative to the intelligent function; Step 2: collecting all measuring point information of the target plant, screening the measuring points meeting the requirements, and evaluating the overall quality of the measuring points meeting the requirements; Step 3: inputting the feasibility weighted importance coefficient of the measuring point relative to the intelligent function and the quality coefficient of the measuring point into the intelligent function evaluation model to evaluate each required intelligent function; The step 2 specifically comprises: Step 2-1: reading all measuring point information of the plant, judging the accuracy and completeness of the measuring points according to the measuring point situation, and screening the measuring points meeting the requirements; the accuracy refers to the degree of consistency between the data obtained by the measuring point and the actual situation; the completeness refers to the interval of the data obtained by the measuring point meeting the requirements of the intelligent function; Step 2-2: evaluating the overall quality of the measuring points meeting the requirements; The overall quality evaluation formula of the measuring point is: Wherein, λ' represents the historical time sequence quality coefficient of the measuring point, and the value range is 0-1; normal working condition point represents the number of normal measurement data in a period of historical data; abnormal working condition point represents the number of abnormal measurement data in a period of historical data; The step 3 specifically comprises: Step 3-1: inputting the quality coefficient of each measuring point as a target variable, the time sequence historical measurement data of the measuring point related parameters and the historical time sequence quality coefficient of each measuring point calculated in step 2 as independent variables into a neural network model, respectively predicting the quality coefficient value of the specified time sequence of each measuring point as the quality coefficient λ of the measuring point; Step 3-2: analyzing and evaluating the feasibility of each intelligent function according to the feasibility weighted importance coefficient ω of each intelligent function corresponding to each measuring point and the quality coefficient λ of each measuring point.

2. The plant intelligent function evaluation method according to claim 1, characterized in that, The step 1 specifically comprises: Step 1-1: analyzing and confirming the production link of the plant corresponding to the demand of the user required intelligent function by decomposing the demand; determining the measuring point information required by the demand for each production link; Step 1-2: performing physical logic analysis on the plant intelligent transformation demand required by the user, and determining the main variable measuring point of each intelligent function according to the physical logic; Step 1-3: the importance coefficient of the main variable measuring point corresponding to the intelligent function is determined as 1, and the correlation of other measuring points to the main variable of the intelligent function is analyzed as the weighted importance coefficient of the measuring points to the feasibility of the intelligent function.

3. The plant intelligent function evaluation method according to claim 2, characterized in that, The formula for calculating the feasibility weighted importance coefficient is: Wherein, ω represents the feasibility weighted importance coefficient of the to-be-evaluated measuring point relative to an intelligent function, and the value range is 0-1; n represents the total number of samples, that is, the number of measuring data of the to-be-evaluated measuring point in a period of time; x i is the i th data measured in a period of time by the factor 1, that is, the master variable measuring point corresponding to the intelligent function of the to-be-evaluated measuring point; i is the i th data measured in a period of time by the factor 2, that is, the to-be-evaluated measuring point; is the average value of the factor 1; is the average value of the factor 2.

4. The plant intelligent function evaluation method according to claim 1, characterized in that, The intelligent function evaluation model is: wherein T m represents the result of the mth intelligent function evaluating the k measuring points, and the range is 0-1; ω jm represents the feasibility weighted importance coefficient of the jth measuring point to the mth intelligent function; λ j represents the quality coefficient of the jth measuring point; According to the requirements of each intelligent function, set the threshold value K of each intelligent function, and the evaluation result exceeding the threshold value K represents that the intelligent function evaluation result meets the standard, that is, it has the condition of intelligent function upgrading and transformation. 5.A plant intelligent function evaluation system, the system comprising: A feasibility weight coefficient module for analyzing the required measuring point information corresponding to the plant intelligent function according to the plant physical operation logic and user measuring point demand analysis, and calculating the feasibility weight coefficient of the measuring point relative to the intelligent function; The overall quality condition evaluation module is used for collecting all the measuring point information of the target factory building, screening the measuring points meeting the requirements, and evaluating the overall quality condition of the measuring points meeting the requirements. And The intelligent function evaluation module is used for inputting the feasibility weighted importance coefficients of the measuring points relative to the intelligent functions and the overall quality conditions of the measuring points into an intelligent function evaluation model to evaluate each required intelligent function. The collection of all the measuring point information of the target factory building, the screening of the measuring points meeting the requirements, and the evaluation of the overall quality condition of the measuring points meeting the requirements specifically include: Step 2-1: reading all the measuring point information of the factory building, judging the accuracy and completeness of the measuring points according to the measuring point conditions, and screening the measuring points meeting the requirements; the accuracy refers to the degree of coincidence between the data obtained by the measuring point and the actual situation; the completeness refers to the interval of the data obtained by the measuring point meeting the requirements of the intelligent function; Step 2-2: evaluating the overall quality condition of the measuring points meeting the requirements; The overall quality condition evaluation formula of the measuring point is: Wherein, λ' represents the historical time sequence quality coefficient of the measuring point; normal working condition point represents the number of normal measurement data in a period of historical data; abnormal working condition point represents the number of abnormal measurement data in a period of historical data; The input of the feasibility weighted importance coefficients of the measuring points relative to the intelligent functions and the overall quality conditions of the measuring points into the intelligent function evaluation model to evaluate each required intelligent function specifically includes: Step 3-1: taking each measuring point quality coefficient as a target variable, inputting the time sequence historical measurement data of the measuring point related parameters and the historical time sequence quality coefficient of each measuring point calculated in step 2 as independent variables into a neural network model, respectively predicting the quality coefficient value of the specified time sequence of each measuring point as the quality coefficient λ of the measuring point; Step 3-2: according to the feasibility weighted importance coefficients ω of each measuring point corresponding to each intelligent function and the quality coefficient λ of each measuring point, analyzing and evaluating the feasibility of each intelligent function.

6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 4 when executing the computer program.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores a computer program, which, when executed by the processor, causes the processor to execute the method of any one of claims 1 to 4.

Images