Design method and device for double-extraction steam turbine of ultra-supercritical unit

Abstract

The application provides a double-extraction steam turbine design method and device for an ultra-supercritical unit, belongs to the field of double-extraction steam turbines, and aims to solve the problems of complex design work, difficult comprehensive consideration, low efficiency and poor effect in the related art.In the method and device, a recommended design scheme can be intelligently analyzed and determined through simple natural language expression of a design task description, the design process is greatly simplified, the design efficiency is improved, in the design process, all parameter design dimensions, dimension performance scores of multiple performance dimensions, and consideration directions such as scheme cost values are considered, the optional design scheme is comprehensively determined as the recommended design scheme in combination with historical design records, the design is considered comprehensively, the design process is intelligent and reasonable, the finally determined recommended design scheme has extremely high reference value, and the design effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of double-extraction steam turbines, and in particular to a design method and device for a double-extraction steam turbine of an ultra-supercritical unit. BACKGROUND

[0002] In today's energy and power field, thermal power generation, as one of the main forms of power generation, continues to play a key role. Ultra-supercritical units have become an important direction for the development of thermal power generation technology due to their ability to significantly improve unit thermal efficiency, reduce coal consumption, and reduce pollutant emissions, and have been widely applied and promoted worldwide.

[0003] The double-extraction steam turbine in an ultra-supercritical unit, as a core component of the unit system, plays a crucial role in the safe and stable operation of the entire unit and energy utilization efficiency. The double-extraction steam turbine extracts steam at different pressure levels within the steam turbine to achieve external heat supply or industrial steam supply, while ensuring efficient power generation. This design concept aims to improve the overall efficiency of energy utilization, meet various energy needs in industrial processes, and meet the requirements of urban central heating, in line with the current development trend of energy cascade utilization.

[0004] With the increasing diversification and complexity of the power market demand, as well as the continuous improvement of energy utilization efficiency and unit operation stability requirements, the design considerations for ultra-supercritical unit double-extraction steam turbines are becoming more and more diverse. Based on this, the difficulties in designing ultra-supercritical unit double-extraction steam turbines not only come from the design level based on empirical formulas and simplified thermodynamic calculation models, which often cannot accurately predict the application of the design scheme, but also from the need for designers to spend time and effort to determine the requirements of all consideration dimensions of the ultra-supercritical unit double-extraction steam turbine based on certain professional knowledge, which brings great difficulty and challenge to the design work. SUMMARY

[0005] The present application provides a design method and device for a double-extraction steam turbine of an ultra-supercritical unit, which is beneficial to improving design efficiency, simplifying design work, and improving design effect in the design work of a double-extraction steam turbine of an ultra-supercritical unit, in order to cope with the difficulty and challenge in the design work.

[0006] In a first aspect, the present application provides a design method for a double-extraction steam turbine of an ultra-supercritical unit. The method comprises:

[0007] obtaining a design task description of the double-extraction steam turbine, the design task description being a natural language expression;

[0008] determining a selectable design scheme according to the design task description, the selectable design scheme containing multiple design parameter dimensions and dimension parameter values of each design parameter dimension;

[0009] inputting the optional design scheme into a pre-constructed cost prediction model and a performance evaluation model of multiple performance dimensions to obtain a corresponding scheme cost value and a dimension performance score of each performance dimension;

[0010] determining a scheme recommendation degree of the optional design scheme in combination with the scheme cost value, the dimension performance scores of all performance dimensions and the pre-acquired historical design record;

[0011] determining a recommended design scheme in the optional design scheme according to the scheme recommendation degree.

[0012] By adopting the above technical solution, the designer only needs to input a design task description expressed in natural language, and the algorithm model can automatically analyze the optional design scheme containing multiple design parameter dimensions, automatically comprehensively evaluate the performance of the optional design scheme in various aspects, finally determine the scheme recommendation degree of the optional design scheme in combination with the historical design record, and finally determine a suitable recommended design scheme, which is beneficial to reducing the workload of the designer, simplifying the design work, fully considering various design dimensions and the historical design record, and greatly improving the design effect.

[0013] Further, the historical design record carries a time stamp, and the historical design record includes a design description record and a selected design scheme;

[0014] The combination of the scheme cost value, the dimension performance scores of all performance dimensions and the pre-acquired historical design record to determine the scheme recommendation degree of the optional design scheme includes:

[0015] determining a recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions;

[0016] filtering a similar design record in the historical design record according to the design task description, and the similarity degree of the design description record of the similar design record to the description of the design task description is higher than a description similarity threshold;

[0017] analyzing a recommendation degree influence coefficient according to the similar design record of the optional design scheme;

[0018] calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

[0019] Further, the determination of the recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions includes:

[0020] assuming that the scheme cost value is c, the i-th dimension performance score is , the recommendation degree base value is , then

[0021] ;

[0022] In the formula, is a preset attention coefficient constant for the i-th performance dimension.

[0023] Further, the analysis of the recommendation degree influence coefficient of the similar design record according to the optional design scheme includes:

[0024] Suppose the selected design scheme of the i-th similar design record in chronological order is , the timestamp is , the optional design scheme is , the current time is , and the recommendation influence coefficient is k, then

[0025] ;

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] In the formula, is a slope extraction function, which represents the slope of the fitting straight line obtained by linear regression of the coordinate points of the similar design record, with the horizontal coordinate being and the vertical coordinate being is a pre-acquired basic influence coefficient.

[0032] Further, the calculation of the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient includes:

[0033] Suppose the recommendation degree base value is , the recommendation influence coefficient is k, and the scheme recommendation degree is z, then

[0034] ;

[0035] In the formula, A is a pre-acquired scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all the dimension confidence degrees.

[0036] In a second aspect, the present application provides a double-extraction steam turbine design device for ultra-supercritical units. The device includes:

[0037] ​An obtaining module is configured to obtain a design task description of a double-extraction steam turbine, the design task description being a natural language expression;

[0038] An understanding module is configured to determine an optional design scheme according to the design task description, the optional design scheme including a plurality of design parameter dimensions and a dimension parameter value of each design parameter dimension;

[0039] An analysis module is configured to input the optional design scheme into a pre-constructed cost prediction model and a performance evaluation model of a plurality of performance dimensions to obtain a scheme cost value and a dimension performance score of each performance dimension;

[0040] A calculation module is configured to determine a scheme recommendation degree of the optional design scheme in combination with the scheme cost value, the dimension performance scores of all performance dimensions, and a pre-obtained historical design record; and

[0041] A recommendation module is configured to determine a recommended design scheme from the optional design scheme according to the scheme recommendation degree.

[0042] Further, the historical design record carries a time stamp, and the historical design record includes a design description record and a selected design scheme;

[0043] The calculation module is further configured to determine the scheme recommendation degree of the optional design scheme in combination with the scheme cost value, the dimension performance scores of all performance dimensions, and the pre-obtained historical design record, including:

[0044] determining a recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions;

[0045] filtering a similar design record from the historical design record according to the design task description, the design description record of the similar design record having a higher similarity degree to the design task description than a description similarity threshold;

[0046] analyzing a recommendation degree influence coefficient according to the similar design record of the optional design scheme;

[0047] calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

[0048] Further, the calculation module is further configured to determine the recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions, including:

[0049] assuming that the scheme cost value is c, the i-th dimension performance score is , the recommendation degree base value is , and

[0050] ;

[0051] In the formula, is a preset attention coefficient constant for the i-th performance dimension.

[0052] Further, the computing module is further configured to analyze the recommendation degree influence coefficient of the similar design record according to the optional design scheme, including:

[0053] Suppose the selected design scheme of the i-th similar design record in chronological order is , the timestamp is , the optional design scheme is , the current time is , and the recommendation influence coefficient is k, then

[0054] ;

[0055] ;

[0056] ;

[0057] ;

[0058] ;

[0059] ;

[0060] In the formula, is a slope extraction function, which represents the slope of the fitting straight line obtained by linear regression of the coordinate points of the similar design record, with the horizontal coordinate being and the vertical coordinate being is a pre-acquired basic influence coefficient.

[0061] Further, the computing module is further configured to calculate the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient, including:

[0062] Suppose the recommendation degree base value is , the recommendation influence coefficient is k, and the scheme recommendation degree is z, then

[0063] ;

[0064] In the formula, A is a pre-acquired scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all dimension confidence degrees.

[0065] In summary, the present application at least includes the following beneficial effects:

[0066] ​Provided are a design method and device for a double-extraction steam turbine of an ultra-supercritical unit, which can simplify design work, improve design efficiency, and optimize design effect.

[0067] It should be understood that the content described in the summary section is not intended to define key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0068] The above and other features, advantages, and aspects of embodiments of the application will become more apparent by describing in detail preferred embodiments thereof with reference to the attached drawings in which:

[0069] Figure 1 A flow chart of a design method for a double-extraction steam turbine of an ultra-supercritical unit is shown in the embodiments of the application;

[0070] Figure 2 A block diagram of a design device for a double-extraction steam turbine of an ultra-supercritical unit is shown in the embodiments of the application. DETAILED DESCRIPTION

[0071] To make the objectives, technical solutions, and advantages of the embodiments of the application clearer, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are some but not all of the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0072] In addition, the term "and / or" herein merely describes an association relationship of associated objects, and indicates that there can be three relationships, for example, A and / or B can represent the three cases of existence of A alone, existence of A and B simultaneously, and existence of B alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0073] The application provides a design method and device for a double-extraction steam turbine of an ultra-supercritical unit, which can simplify design work, improve design efficiency, and optimize design effect based on an intelligent algorithm model.

[0074] In a first aspect, the embodiments of the application disclose a design method for a double-extraction steam turbine of an ultra-supercritical unit.

[0075] Figure 1 A flow chart of a design method for a double-extraction steam turbine of an ultra-supercritical unit is shown in the embodiments of the application.

[0076] With reference to Figure 1 The method specifically comprises the following steps:

[0077] S110: Obtain a design task description of a double-extraction steam turbine, the design task description being a natural language expression.

[0078] As for the obtaining method of the design task description, it can be obtained based on text input, audio input, video input or man-machine dialogue, etc. The original file of the design task description can be a design contract or a design project text, an audio or video of communication records with a customer or a dialogue process record of a designer with a general or special-purpose large model, etc. After the text information contained in the original file is extracted, arranged and manually reviewed based on known information processing technology, the design task description in the form of a natural language expression is formed. Of course, the design task description can also be a direct natural language input of a designer.

[0079] S120: Determine a selectable design scheme according to the design task description, the selectable design scheme containing multiple design parameter dimensions and dimension parameter values of each design parameter dimension.

[0080] The method of this step is realized based on natural language processing technology and a decision tree pre-constructed based on industry consensus. The natural language processing technology is used to analyze the design task description, and the decision tree is used to determine the selectable design scheme based on the analysis result.

[0081] The natural language description of the design task is deeply analyzed by using the natural language processing technology, and the key information is accurately extracted, including but not limited to:

[0082] Performance index: For example, “design a double-extraction steam turbine of an ultra-supercritical unit, the expected power generation is 600 MW, the high-pressure extraction steam pressure is stabilized at 4-5 MPa, and the low-pressure extraction steam flow meets the heating demand of 150 t / h”, the core performance points such as “600 MW power generation”, “4-5 MPa high-pressure extraction steam pressure” and “150 t / h low-pressure extraction steam flow” are accurately refined.

[0083] Operating condition: If it is mentioned that “the steam turbine will be installed in a high-altitude and cold area, the environmental temperature is as low as -20°C, and the sand content in the air is high”, the operating condition key details such as “high altitude”, “low temperature” and “sand environment” are carefully extracted. These factors will significantly affect the material selection, cooling system design and protection measures of the equipment.

[0084] Reliability and maintenance requirements: For example, “high reliability is required, the average trouble-free operation time is not less than 5000 hours, and the maintenance should be convenient and efficient, and the single maintenance time is not more than 48 hours”, the key requirements such as “high reliability” and “short maintenance time” are clearly captured, which will play a key role in component selection, structure design optimization and maintenance strategy planning, etc.

[0085] Regarding the construction of the decision tree, the main content is the setting of the decision tree nodes and branches. For example, taking the power generation power as the root node: according to industry experience, for different power generation power ranges (such as 300-500MW, 500-800MW, etc.), the approximate value range or optional scheme branch of the subsequent related parameters is determined. For example, when the power generation power is around 600MW, the main steam pressure may be more appropriate in the range of 28-32MPa, which forms a branch in the dimension of main steam pressure.

[0086] Consider the extraction steam parameter branch: for extraction steam parameters such as high-pressure extraction steam pressure and low-pressure extraction steam flow, further subdivide the branches. For example, when the high-pressure extraction steam pressure is in the range of 4-5MPa, it may correspond to a specific range of stages (such as 8-10 stages) and extraction port position range (such as after the 4th-6th stage of the high-pressure cylinder) of the intermediate-pressure cylinder. These branches are constructed based on the parameter correlation determined by a large number of actual cases and theoretical calculations in the industry.

[0087] Combine the running environment branch: when the running environment is high altitude, cold and dusty, in the material selection branch, it may point to special alloy materials that are resistant to high temperature, low temperature and sand erosion; in the cooling system branch, it may tend to adopt a cooling method that combines air cooling and water cooling and has a sand dust blocking design. Each branch has a corresponding parameter value range or specific selection recommendation, which is based on the summary and refinement of the running experience of equipment in similar environments in the industry.

[0088] Of course, considering the reliability of the decision tree, confidence can also be added to the branches of the decision tree. The confidence is realized based on data statistics and experience evaluation. Specifically, for example, by statistically analyzing the historical data of a large number of similar design projects in the industry, combined with expert experience judgment, a confidence is given to each branch of the decision tree. For example, for the case where the power generation power is 600MW and the high-pressure extraction steam pressure is in the range of 4-5MPa, the 9-stage scheme is selected for the intermediate-pressure cylinder. If 40 out of the past 50 similar projects have adopted similar configurations and run well, the confidence of this branch can be set to 0.8 (40 / 50). For some emerging technologies or less applied parameter combinations, the confidence may be relatively low, such as the scheme of using a new type of high-temperature resistant coating, since the actual application cases are few, its confidence may be only 0.3-0.5.

[0089] Based on the key information processed by natural language processing technology and the constructed knowledge graph, the decision tree can determine the optional scheme. For example, starting from the root node of the decision tree, according to the key information extracted from the design task, traverse along the corresponding branch, combine the values of each parameter dimension, and generate a complete optional design scheme. For example, a scheme can be: main steam pressure 30 MPa (confidence 0.7), main steam temperature 620°C (confidence 0.8), high-pressure cylinder 10 stages (confidence 0.85), low-pressure cylinder 6 stages (confidence 0.8), high-pressure extraction port after the 5th stage (confidence 0.9), extraction pipe diameter 0.4 m (confidence 0.75), etc. Each parameter dimension carries its corresponding confidence label, which reflects the reliability of the parameter value under the current design task and industry experience, providing an important reference for subsequent scheme evaluation and optimization.

[0090] Based on the above, the optional design scheme can be determined, which is expressed as a multi-dimensional vector and can carry the confidence of each parameter design dimension.

[0091] S130: input the optional design scheme into the pre-constructed cost prediction model and the performance evaluation model of multiple performance dimensions, to obtain the corresponding scheme cost value and the dimension performance score of each performance dimension.

[0092] Since the optional design scheme is essentially the dimension parameter value of all parameter design dimensions, reflecting the overall design requirements of the double-extraction steam turbine, based on these requirements and industry experience data, design experience records, etc., the cost and performance of the double-extraction steam turbine in multiple aspects can be predicted. The pre-trained cost prediction model is used to analyze the scheme cost value of the optional design scheme, and the pre-constructed performance evaluation model is used to analyze the dimension performance score of a certain performance dimension based on the optional design scheme.

[0093] Regarding the cost prediction model, in one example, the optional design scheme is substituted into the cost prediction model , and multiple cost components such as material cost , manufacturing process cost , equipment selection cost , and operation and maintenance cost are calculated. The comprehensive cost score is calculated by comparing each cost component with the pre-set cost target value or reference value, and according to the cost score conversion function . For example, assuming that the total target cost is and the actual total cost is , then:

[0094] ;

[0095] For example, the conversion function is:

[0096] ;

[0097] Based on the above, the scheme cost value of the optional design scheme can be analyzed.

[0098] Regarding the performance evaluation model, for example, the power generation efficiency evaluation model, the steam extraction performance evaluation model, and the reliability evaluation model.

[0099] Regarding the power generation efficiency dimension performance score , the optional design scheme is substituted into the power generation efficiency evaluation model to calculate the power generation efficiency prediction value , and then according to the pre-set power generation efficiency target value and the performance score conversion function , the power generation efficiency dimension performance score is calculated:

[0100] ;

[0101] For example, assuming that the conversion function is a linear function:

[0102] ;

[0103] Regarding the steam extraction performance evaluation model , the optional design scheme is substituted into the steam extraction performance evaluation model to calculate the high-pressure steam extraction pressure deviation , the low-pressure steam extraction flow deviation , and other indicators, and then according to the deviation and the performance score conversion function , the steam extraction performance dimension performance score is determined. For example, for the high-pressure steam extraction pressure deviation, the conversion function is:

[0104] ;

[0105] In the formula, is the pre-set high-pressure steam extraction pressure. Similarly, the low-pressure steam extraction performance score can be obtained, which is not described in detail. Assuming that the steam extraction performance dimension performance score is obtained by weighted average of the high-pressure steam extraction and low-pressure steam extraction performance scores, and the weights are , then:

[0106] ;

[0107] Regarding the reliability evaluation model , the optional design scheme is substituted into the reliability evaluation model , the reliability index is calculated , and then the reliability index and the performance score conversion function determine the reliability dimension performance score:

[0108] ;

[0109] For example, assuming that the value range of the reliability index is between 0 and 1, and the conversion function is:

[0110] ;

[0111] Similarly, the performance scores of other dimensions are calculated, which are not listed one by one.

[0112] S140: Determine the scheme recommendation degree of the selectable design scheme in combination with the scheme cost value, the dimension performance scores of all performance dimensions, and the pre-acquired historical design records.

[0113] The method of this step specifically includes: determining a recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions; filtering similar design records in the historical design records according to the design task description, wherein the design description records of the similar design records have a description similarity with the design task description higher than a description similarity threshold; analyzing a recommendation degree influence coefficient according to the similar design records of the selectable design scheme; and calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

[0114] In one example, the determination of the recommendation degree base value based on the scheme cost value and the dimension performance scores of all performance dimensions includes: setting the scheme cost value as c, the i-th dimension performance score as , and the recommendation degree base value as , wherein , in the formula, is a preset attention coefficient constant relative to the i-th performance dimension.

[0115] In one example, the analysis of the recommendation degree influence coefficient according to the similar design records of the selectable design scheme includes: setting the selected design scheme of the i-th similar design record in the chronological order as , the time stamp as , the selectable design scheme as , the current time as , and the recommendation influence coefficient as k, wherein

[0116] ;

[0117] ;

[0118] ;

[0119] ;

[0120] ;

[0121] ;

[0122] wherein, is a slope extraction function, which represents the slope of the fitting line obtained by linear regression of the coordinate points of the similar design records with the horizontal coordinate being and the vertical coordinate being , and is a pre-obtained basic impact coefficient.

[0123] In one example, the calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree impact coefficient comprises: setting the recommendation degree base value as , the recommendation impact coefficient as k, and the scheme recommendation degree as z, then

[0124] , wherein A is a pre-obtained scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all the dimension confidence degrees, for example, equal to the sum or average of all the dimension confidence degrees.

[0125] It should be understood that the aforementioned recommendation degree base value is negatively correlated with the scheme cost value and positively correlated with each dimension performance score, and the design can also be other consensus structures. The formula structure specially designed in the method of this step can guarantee that the result range of the recommendation degree base value is between 0 and 1. In addition, regarding the recommendation degree impact coefficient, it can also be associated with only one or two of , so as to adaptively adjust the formula structure. Correspondingly, when the formula structure of the recommendation degree base value and the recommendation degree impact coefficient is changed, the formula structure of the scheme recommendation degree can also be adaptively adjusted. In summary, the specific determination process of the scheme recommendation degree can also be implemented in other forms, which will not be enumerated and introduced here.

[0126] S150: determining a recommended design scheme from the selectable design schemes according to the scheme recommendation degree.

[0127] In one example, after the scheme recommendation degrees of all the selectable design schemes are determined, one or a specified number of selectable design schemes with the highest recommendation degree can be recommended to the user as the recommended design scheme.

[0128] In another example, when multiple recommended design schemes are required, in order to enrich the content of the recommended design scheme, the optional design schemes can also be sorted in order of scheme recommendation degree from high to low to form an optional scheme set, the first optional design scheme is selected as the recommended design scheme, and the optional scheme set discards the selected optional design scheme and the optional design scheme with a vector similarity to the selected optional design scheme higher than a preset recommended similarity threshold, the foregoing actions are repeatedly performed until the number of selected optional design schemes reaches a specified number threshold, and the selected optional design schemes are taken as the recommended design schemes.

[0129] The user can select a selected design scheme of the double-extraction steam turbine from the recommended design schemes, adjust a recommended design scheme to form a new design scheme as the selected design scheme, or discard all recommended design schemes to construct the selected design scheme by himself / herself.

[0130] In summary, the method can intelligently analyze and determine the recommended design scheme through a simple design task description expressed in natural language, greatly simplifies the design process, and is beneficial to improving the design efficiency. In the design process, not only the design dimensions of all parameters, the dimension performance scores of multiple performance dimensions, and the scheme cost value and other consideration directions are considered, but also the historical design records are combined to comprehensively determine the optional design scheme as the recommended design scheme. The design is considered comprehensively, the design process is intelligent and reasonable, the finally determined recommended design scheme has a very high reference value, and the design effect is improved.

[0131] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action order described, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0132] In a second aspect, the embodiments of the present application disclose a double-extraction steam turbine design device for ultra-supercritical units. The device can be implemented as a server for design work or contained in a server.

[0133] Figure 2 A block diagram of a double-extraction steam turbine design device for ultra-supercritical units in the embodiments of the present application is shown.

[0134] Referring to Figure 2 , the device specifically includes:

[0135] The acquisition module 210 is configured to acquire a design task description of a double-extraction steam turbine, and the design task description is expressed in natural language.

[0136] an understanding module 220 configured to determine a plurality of alternative design schemes according to the design task description, the alternative design schemes comprising a plurality of design parameter dimensions and dimension parameter values of each design parameter dimension;

[0137] an analysis module 230 configured to input the alternative design schemes into a pre-built cost prediction model and a plurality of performance dimension performance evaluation models to obtain corresponding scheme cost values and dimension performance scores of each performance dimension;

[0138] a calculation module 240 configured to determine a scheme recommendation degree of the alternative design schemes in combination with the scheme cost values, the dimension performance scores of all performance dimensions, and pre-acquired historical design records; and

[0139] a recommendation module 250 configured to determine a recommended design scheme from the alternative design schemes according to the scheme recommendation degree.

[0140] Further, the historical design records are provided with time stamps, and the historical design records comprise design description records and selected design schemes.

[0141] The calculation module 240 is further configured to determine the scheme recommendation degree of the alternative design schemes in combination with the scheme cost values, the dimension performance scores of all performance dimensions, and the pre-acquired historical design records, which comprises:

[0142] determining a recommendation degree base value based on the scheme cost values and the dimension performance scores of all performance dimensions;

[0143] filtering similar design records from the historical design records according to the design task description, the similarity degree of the design description records of the similar design records to the design task description being higher than a description similarity threshold;

[0144] analyzing a recommendation degree influence coefficient according to the similar design records of the alternative design schemes;

[0145] calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

[0146] Further, the calculation module 240 is further configured to determine the recommendation degree base value based on the scheme cost values and the dimension performance scores of all performance dimensions, which comprises:

[0147] assuming that the scheme cost value is c, the i-th dimension performance score is , the recommendation degree base value is , and

[0148] ;

[0149] In the formula, A preset attention coefficient constant for the i-th performance dimension.

[0150] Further, the computing module 240 is further configured to analyze the recommendation degree influence coefficient of the similar design record according to the optional design scheme, including:

[0151] Supposing the selected design scheme of the i-th similar design record in the time stamp order is , the time stamp is , the optional design scheme is , the current time is , and the recommendation influence coefficient is k, then

[0152] ;

[0153] ;

[0154] ;

[0155] ;

[0156] ;

[0157] ;

[0158] In the formula, is a slope extraction function, which represents the slope of the fitting straight line obtained by linear regression of the coordinate points of the similar design record with the horizontal coordinate being and the vertical coordinate being is a pre-acquired basic influence coefficient.

[0159] Further, the computing module 240 is further configured to calculate the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient, including:

[0160] Supposing the recommendation degree base value is , the recommendation influence coefficient is k, and the scheme recommendation degree is z, then

[0161] ;

[0162] In the formula, A is a pre-acquired scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all the dimension confidence degrees.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the foregoing method embodiments, which will not be described here again. ​

[0164] To sum up, the present application contains at least the following beneficial effects:

[0165] The application provides a double-extraction steam turbine design method and device for a supercritical unit, which can simplify design work, improve design efficiency and optimize design effect.

[0166] The above description is merely preferred embodiments of the present application and a description of the principles of the technology used. Those skilled in the art should understand that the disclosed range of the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A design method of a double-extraction steam turbine of an ultra-supercritical unit, characterized in that, The method comprises the following steps: obtaining a design task description of a double-extraction steam turbine, the design task description being a natural language expression; determining a selectable design scheme according to the design task description, the selectable design scheme comprising a plurality of design parameter dimensions and a dimension parameter value of each design parameter dimension; inputting the selectable design scheme into a pre-constructed cost prediction model and a performance evaluation model of a plurality of performance dimensions to obtain a corresponding scheme cost value and a dimension performance score of each performance dimension; combining the scheme cost value, the dimension performance score of all performance dimensions and a pre-obtained historical design record to determine a scheme recommendation degree of the selectable design scheme; determining a recommended design scheme in the selectable design scheme according to the scheme recommendation degree; the historical design record carries a timestamp, and the historical design record comprises a design description record and a selected design scheme; the combining the scheme cost value, the dimension performance score of all performance dimensions and the pre-obtained historical design record to determine the scheme recommendation degree of the selectable design scheme comprises: determining a recommendation degree base value based on the scheme cost value and the dimension performance score of all performance dimensions; screening a similar design record in the historical design record according to the design task description, the design description record of the similar design record having a high similarity degree with the design task description higher than a description similarity threshold; analyzing a recommendation degree influence coefficient according to the similar design record of the selectable design scheme; calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

2. The method of claim 1, wherein, the determining the recommendation degree base value based on the scheme cost value and the dimension performance score of all performance dimensions comprises: Let the scheme cost value be c, the i-th dimension performance score be , and the recommendation degree base value be , then In the formula, is a constant of the attention coefficient preset for the i-th performance dimension.

3. The method of claim 1, wherein, the analyzing the recommendation degree influence coefficient according to the similar design record of the selectable design scheme comprises: Let the selected design scheme of the i-th similar design record in chronological order be , the timestamp be , the optional design scheme be , the current time be , and the recommended influence coefficient be k, then In the formula, is a slope extraction function, which represents the slope of the fitting line obtained by linear regression of the similar design record coordinate points with the horizontal coordinate and the vertical coordinate , is a pre-acquired basic influence coefficient.

4. The method of claim 1, wherein, the calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient comprises: Let the recommended degree base value be , the recommended influence coefficient be k, and the scheme recommended degree be z, then wherein A is a pre-obtained scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all dimension confidence degrees.

5. An ultra-supercritical unit double-extraction steam turbine design apparatus, characterized by, The method comprises the following steps: an obtaining module (210) is configured to obtain a design task description of a double-extraction steam turbine, the design task description being a natural language expression; an understanding module (220) is configured to determine a selectable design scheme according to the design task description, the selectable design scheme comprising a plurality of design parameter dimensions and a dimension parameter value of each design parameter dimension; an analysis module (230) is configured to input the selectable design scheme into a pre-constructed cost prediction model and a performance evaluation model of a plurality of performance dimensions to obtain a corresponding scheme cost value and a dimension performance score of each performance dimension; a calculation module (240) is configured to combine the scheme cost value, the dimension performance score of all performance dimensions and a pre-obtained historical design record to determine a scheme recommendation degree of the selectable design scheme; and a recommendation module (250) is configured to determine a recommended design scheme in the selectable design scheme according to the scheme recommendation degree; the historical design record carries a timestamp, and the historical design record comprises a design description record and a selected design scheme; The computing module (240) is further configured to determine a scheme recommendation degree of the optional design scheme based on the combination scheme cost value, the dimension performance score of all performance dimensions, and the pre-acquired historical design record, including: determining a recommendation degree base value based on the scheme cost value and the dimension performance score of all performance dimensions; screening similar design records in the historical design record according to the design task description, and the design description record of the similar design record having a description similarity to the design task description higher than a description similarity threshold; analyzing a recommendation degree influence coefficient according to the similar design record of the optional design scheme; calculating the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient.

6. The apparatus of claim 5, wherein, The computing module (240) is further configured to determine the recommendation degree base value based on the scheme cost value and the dimension performance score of all performance dimensions, including: Let the scheme cost value be c, the i-th dimension performance score be , and the recommendation degree base value be , then In the formula, is a constant of the attention coefficient preset for the i-th performance dimension.

7. The apparatus of claim 5, wherein, The computing module (240) is further configured to analyze the recommendation degree influence coefficient according to the similar design record of the optional design scheme, including: Let the selected design scheme of the i-th similar design record in chronological order be , the timestamp be , the optional design scheme be , the current time be , and the recommended influence coefficient be k, then In the formula, is a slope extraction function, which represents the slope of the fitting line obtained by linear regression of the similar design record coordinate points with the horizontal coordinate and the vertical coordinate , is a pre-acquired basic influence coefficient.

8. The apparatus of claim 5, wherein, The computing module (240) is further configured to calculate the scheme recommendation degree according to the recommendation degree base value and the recommendation degree influence coefficient, including: Let the recommended degree base value be , the recommended influence coefficient be k, and the scheme recommended degree be z, then wherein A is a pre-acquired scheme confidence degree, the dimension parameter value of the design parameter dimension carries a dimension confidence degree based on the design task description, and the scheme confidence degree is positively correlated with all dimension confidence degrees.

Images