Steam system based on data technology

Abstract

The invention discloses a steam system implemented based on a data technology, which relates to the technical field of steam systems and comprises a cockpit module, a monitoring sensing module, an operation analysis module, an auxiliary operation module, an operation optimization module, a knowledge management module and a system management module in a steam pipe network management process. The system is a management system serving actual business and assisting steam regulation and control operation, and through soft closed-loop management from data perception to analysis assistance, to control guidance and to business optimization, by means of a mode of combining online management and offline management, the purposes of monitoring perception, problem prediction, problem pushing, and the like are truly achieved. A series of closed-loop management and control such as problem solving, effect checking and continuous improvement are achieved, management decision is assisted, and management upgrading from post-event management to pre-event management and prevention management and control is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of steam systems, and in particular to a steam system implemented based on data technology. Background Art

[0002] Steam is an important energy medium in the industrial production process. The steam pipe network system is widely used in the systems of petroleum, chemical, biochemical, food, pharmaceutical and other industries as well as cities and parks, and is mainly used for the transportation of energy within parks and factories. Taking industry as an example, the steam pipe network is directly related to the operation, dispatching and energy allocation of the entire system, and indirectly affects the stable operation of parks and factories, and affects the key economic indicators such as product quality, quality, output and energy consumption of equipment. It is an important channel for transporting power and energy, and it is also the lifeline connecting various production and operation links. Through the construction of steam energy management related applications, the steam energy collection standards of various levels are sorted out, the steam energy data management mode is standardized, and energy management tools and methods such as steam energy data basic model and steam energy use analysis and prediction model are established. They are used in combination with lean manufacturing tools and methods such as equipment availability analysis, downtime loss analysis, production balance analysis, and value stream analysis to effectively coordinate various elements such as energy, production, equipment, finance, and information, deeply reduce energy waste, volatility and inflexibility, and achieve energy productivity optimization.

[0003] On this basis, after searching the patent website, Chinese patent announcement number CN212511104U discloses a data visualization steam cooling system. On the basis of reducing the temperature of superheated steam to improve production safety, production efficiency and energy saving and consumption reduction, the system automatically displays the injection water flow rate and steam flow rate as well as the ratio between the two, realizing the visualization of the cooling system data;

[0004] It can be seen that there are shortcomings in the above patent application: At present, most industrial enterprises rely on scheduling experience and offline collaborative management and control mode for steam management. In the actual operation of the steam pipeline network, due to the many management and control interfaces involved, the experience, techniques, levels and cognition of users and operators are different, resulting in uneven performance of pipeline operation, unstable production, quality and operating condition control, and large differences. In addition, it is difficult to solidify operating experience, unify operating strategies, standardize process management, and lack decision-making basis for process parameter optimization, which affects the efficiency of steam system use.

[0005] In view of the above problems, a method for realizing a steam system based on data technology is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a steam system based on data technology, which is operated by the present device, thereby solving the problem that most industrial enterprises, for steam management, remain in a management and control mode that relies on scheduling experience and offline collaboration. In the actual operation of the steam pipeline network, due to the many management and control interfaces involved, and the different experiences, techniques, levels and cognitions of users and operators, the operation performance of the pipeline network varies greatly, and the output, quality and operating condition control are unstable and vary greatly. In addition, it is difficult to solidify operating experience, unify operating strategies, standardize process management, and lack decision-making basis for process parameter optimization.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a data-based steam system, including a cockpit module, a monitoring and perception module, an operation analysis module, an auxiliary operation module, an operation optimization module, a knowledge management module and a system management module in the steam pipe network management process; the cockpit module in the steam pipe network management process includes three parts: key indicators, a general view of the pipe network and a general view of energy flow. Based on a general view of a steam pipe network, the key indicator data of the steam pipe network operation is displayed, counted and analyzed in a combination of graphics, text and numbers, so as to assist a decision-making layer to control the comprehensive overview of the steam pipe network operation, business management and cost-effectiveness, quickly locate abnormal information of the steam pipe network operation, and scientifically and effectively formulate optimization strategies;

[0008] The monitoring and perception module mainly manages and monitors the pipeline network by classification, grading, role and scenario, and comprehensively perceives the steam supply, transportation, use and loss. Based on the dynamic balance model, it dynamically monitors each steam production and use situation, and comprehensively and dynamically perceives from large to small, from primary to secondary, and from coarse to fine.

[0009] The operation analysis module analyzes the operation data of the pipeline network based on the data of the monitoring perception module and the data output by the algorithm model in combination with the actual management business. It mainly includes consumption analysis, comparative analysis, and abnormality analysis modules. Through the analysis module, it aims to analyze the abnormality, consumption, balance, performance, and cost of the operation process of the pipeline network;

[0010] The auxiliary operation module mainly assists users at the decision-making, management and execution levels to perform dynamic balance, steady-state adjustment and auxiliary operations of the pipeline network. Its main functions include ensuring steam supply, avoiding excess, analyzing the situation, auxiliary scheduling and terminal control, etc.

[0011] The operation optimization module analyzes excellent operation samples and abnormal operation samples of the pipeline network based on a large amount of historical data and steady-state control sample data, so as to find the optimization direction of pipeline network operation, analyze the current working conditions in combination with dynamic data, and provide collaborative optimization operation guidance based on the existing working conditions;

[0012] The knowledge management module includes report management and knowledge sample library management.

[0013] Report management mainly records and extracts important information from each module group to form reports that are important for daily management, such as operation management reports, exception reports, optimization reports, energy efficiency reports, etc.; the knowledge sample library management mainly stores and records the valuable data, samples and knowledge information mined by the system in an orderly manner to facilitate the formation of data assets and the inheritance of experience.

[0014] Preferably, the key indicators include main supply balance indicators of the steam network, energy flow indicators, consumption and loss indicators, unit consumption indicators, abnormal energy consumption and emission indicators; the overall view of the network uses graphic configuration to display the overall view of the first-level network of the whole plant in a macroscopic way, and to display the operation status of the main equipment in the first-level network; the overall view of the steam energy flow calculates the energy flow based on the materials and process parameters of the steam network, and draws an overall view of the energy flow balance, which can be synchronized with the overall view of the network or switched to display, to assist the decision-making layer in quickly grasping the operation information of the network.

[0015] Preferably, the monitoring and sensing module includes: 1) supply situation monitoring

[0016] Monitor all supply points in the pipe network and the main process parameters that affect supply, such as the amount of coal used by the boiler, the air volume, etc., the data related to the operation of the process waste heat boiler, the heat load, the heat exchange temperature and other parameters. At the same time, various charts such as trend charts are used for auxiliary display;

[0017] 2) Pipeline network equipment

[0018] Pipeline network equipment monitoring mainly monitors the parameters of pipeline network equipment such as desuperheaters, pressure reducers, desuperheating and pressure reducing devices, vent valves, distribution tables, flash tanks, condensers, etc. Capture the most core data for monitoring, such as valve position, water replenishment volume, delivery volume, condensing temperature, etc.

[0019] 3) Steam turbine operation status

[0020] Focus on monitoring the operation of the steam turbine. The main monitoring indicators include core indicators such as steam consumption, extraction volume, standby pressure, condensate volume, power generation or channel equipment load, as well as temperature, temperature difference, superheat, pressure, effective work, enthalpy value, etc. during operation;

[0021] 4) Pipeline network usage

[0022] It is mainly for users other than power steam users in the pipeline network. According to the situation of on-site sensors, the device, section, or even specific equipment can be used as the monitoring object. The main monitoring indicators include pressure, pressure difference, temperature, temperature difference, flow, superheat, dryness, etc.

[0023] 5) Pipeline network loss

[0024] Based on the dynamic balance model of the pipeline network, the system dynamically analyzes the loss of five levels of pipeline networks, such as steam material loss and energy loss, down to the user point. It issues an alarm for deviations or large losses;

[0025] 6) Abnormality warning

[0026] Abnormal alarm warning is mainly based on dynamic balance model and steady-state model, drawing dynamic multi-parameter and single-parameter steady-state control base and dynamic reference curve. Based on this, real-time dynamic and actual working conditions are compared and analyzed, and single or multiple parameters that deviate from the steady-state value are warned to assist in the adjustment and control of indicators.

[0027] Preferably, the operation analysis module includes: 1) consumption analysis

[0028] This module mainly analyzes the overall steam consumption of the steam network, the steam consumption of the five-level network, the steam consumption of each user point, and the condensate loss. The analysis includes trend analysis, proportion analysis, component analysis, and unit consumption analysis.

[0029] 2) Abnormal analysis

[0030] Abnormal analysis mainly determines the warning items based on the monitoring and early warning module, analyzes the abnormal items, such as the correlation of abnormal indicators, main causes, and causal links, and records the abnormal indicators and corresponding working conditions to form abnormal analysis reports, and automatically accumulates negative sample data as the iteration basis of the steady-state model to assist in the adjustment and control of indicators;

[0031] 3) Feature analysis

[0032] The main cause analysis and causal link determination are carried out for the performance data, abnormal data and optimization data in the operation of the pipeline network, and the influencing factors of the core data are dynamically displayed. The data concerned by the user and the related features can be queried and visualized;

[0033] 4) Balance analysis

[0034] According to the actual business, the overall pipeline network is dynamically balanced, with energy balance as the main factor and materials as the auxiliary factor. Balance analysis is also conducted on the five levels and major users. The overall pipeline network operation is included in the dynamic balance system, and the balance results are dynamically analyzed;

[0035] 5) Energy flow analysis

[0036] Conduct energy flow analysis and energy efficiency analysis on the five-level pipeline network and each user point, display the analysis results, conduct rationality analysis on energy flow changes, and conduct statistics and analysis on parameters with large deviations and abnormal energy flow fluctuations. Pay attention to its change range, impact area, and macroscopic impact on upper and lower level steam, etc.;

[0037] 6) Pre-alarm analysis

[0038] This module mainly analyzes alarm and warning indicators, such as alarm frequency, area, attributes, etc., in order to provide decision-making basis for subsequent adjustments and improvements;

[0039] 7) Performance Analysis

[0040] This module mainly conducts statistical analysis on the main management and control performance indicators, with a frequency of no more than 1 hour / time. The analysis results are presented, and comparative analysis is conducted in the form of team rankings, daily statistics, and weekly statistics. In combination with historical operation conditions, comprehensive and continuous analysis and evaluation are conducted;

[0041] 8) Comprehensive cost analysis

[0042] This module mainly analyzes the steam cost allocated to each user point based on the performance analysis results, and combines the steady-state operation part of historical data as a benchmark, providing standards and basis for current cost control.

[0043] Preferably, the auxiliary operation module includes: 1) steam supply guarantee

[0044] Steam supply is guaranteed based on dynamic balance and demand forecast, and five levels of steam control parameters are operated to ensure supply, such as adjusting steam pressure, temperature, flow, energy, and the use of temperature and pressure reducers;

[0045] 2) Excess steam

[0046] Steam oversupply prevention is based on dynamic balance and demand forecasting, and pre-adjusts the five levels of steam control parameters to prevent abnormal steam network venting, abnormal use of temperature and pressure reducers, abnormal fluctuations in steam extraction, and reduced steam heat exchange efficiency due to excess material and energy supply;

[0047] 3) Situation prediction

[0048] This module is mainly based on a forecasting model with multiple algorithms and multi-dimensional forecasting. It combines the actual supply, demand and consumption data and dynamic balance to predict the changing trend of the supply and demand side, and macroscopically control the changing situation of the overall pipeline network. At the same time, it classifies and classifies the changing trend of each gas consumption end, focusing on presenting the most important factors affecting the balance of the pipeline network.

[0049] 4) Scheduling analysis

[0050] Through the data from the above-mentioned monitoring, early warning, analysis and situation prediction modules, a macro-situation change graph of the pipeline network is formed to assist in dispatching and allocating steam balance to maintain the steady-state operation of the pipeline network;

[0051] 5) Terminal Control

[0052] Conduct data analysis on multiple user ends and control ends, analyze abnormal operation fluctuations and abnormal gas usage, such as energy consumption analysis, energy efficiency analysis, and trend analysis, and provide operation strategies for optimization, maintenance, and degradation improvement.

[0053] Preferably, the operation optimization module includes: 1) Control optimization, auxiliary scheduling, and auxiliary tuning of the macro operation of the pipeline network, such as auxiliary plant-level macro control of overall energy consumption, energy efficiency, material consumption, condensate recovery, etc.; 2) Balance optimization, based on the prediction and steady-state operation model, the overall pipeline network is dynamically optimized for balance. If the prediction model is likely to be emptied, the supply side is adjusted in advance, and the needs of terminal and pipeline network optimization are combined to form a synergistic balance optimization; 3) Supply optimization, supply-side optimization, is to adjust to the optimal supply under the premise of ensuring steam supply, such as gradually increasing the supply load to the precise according to the characteristics of the dynamic changes of the pipeline network. For the load, the system will provide control parameters for time control and target control at the same time to assist in supply optimization; 4) Terminal optimization. The user end has many users and large fluctuations, making it difficult to accurately control. Assisted terminal tuning is based on the terminal's operating data. Under the premise of ensuring the overall network stability, adjustments are made to the terminal users. The optimization directions are mainly gas volume, temperature, pressure, and effective steam work; 5) Performance evaluation is mainly to evaluate the performance before and after collaborative optimization, evaluate the current performance, and perform trend analysis on the results, display excellent and poor situations, and rank the overall performance of the team.

[0054] Preferably, the system management module includes:

[0055] 1) Organization management Organization management is to manage the organizational structure and departments in the system, such as regulating organizational process changes, content changes, etc. Organization management mainly includes functions such as adding, modifying and deleting organizations; 2) User management, manages users and manages permissions according to roles. The background can perform management operations such as user registration, change, and deregistration. User management mainly includes functions such as adding users, associating users with organizations, modifying user information, freezing and unfreezing users; 3) Permission management, manages system permissions according to different user departments and roles; 4) Security management, including menu management, role management, and user log management. Menu management is mainly used to display all function menus of the system; role management mainly includes functions such as adding roles, modifying roles, deleting roles, associating user roles, and authorizing roles; user logs are mainly used to audit user operations; 5) Audit management, mainly audits the operations of system administrators and security administrators; 6) Indicator management, manages process card indicators and performance indicators in the pipeline process, including point changes, formula modifications, and process card indicator boundary modifications.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. This paper proposes a steam system based on data technology. The system is a management system that serves actual business and assists steam control and operation. Through soft closed-loop management from data perception to analysis assistance, control guidance, and business optimization, it truly realizes a series of closed-loop control from monitoring perception, foreseeing problems, pushing problems, to solving problems, testing effects, and continuous improvement, assisting management decision-making, and upgrading management from post-management to pre-management and preventive control.

[0058] 2. The system gathers, manages, compiles statistics and analyzes data related to the steam network and its physical properties, processes, performance, quality, environment, operations, etc., uses algorithms to establish data models, and forms core functions such as driving, sensing, predicting, analyzing, assisting, and optimizing the operation status of the steam network, so as to achieve the purpose of assisting the operation of the steam network, steady-state management, optimizing energy efficiency, improving steam utilization, reducing energy loss and abnormal fluctuations. The system has four innovative points, including innovation in control mode, innovation in perception mode, innovation in dynamic balance of the network, and innovation in steady-state optimization;

[0059] 3. In terms of economic benefits, the system configures high-quality steam for key users, improves the steam energy efficiency of equipment, reduces abnormal consumption, and reduces the evaluation energy cost. The system dynamically optimizes energy supply, stabilizes pipeline operation, and optimizes energy configuration. In terms of management performance, it monitors the steam supply and consumption of each user, unifies the energy unit measurement, and realizes the connection and dynamic association of upstream and downstream information, which can maintain downstream production stability, ensure the stable operation of the steam pipeline network, avoid pressure overlimit and emergency discharge, and ensure safe production. In terms of social benefits, the system responds to the national digital strategy and the guidance of local data construction policies, deeply combines energy conservation and consumption reduction with digital construction, uses digital mining to empower the energy-saving field, practices the deep integration of informationization and industrialization, and improves the working efficiency of the steam system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a schematic diagram of the structure of a steam system implemented based on data technology in the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings.

[0063] Combination Figure 1 , a steam system based on data technology, including a cockpit module, a monitoring perception module, an operation analysis module, an auxiliary operation module, an operation optimization module, a knowledge management module and a system management module in the steam network management process; the cockpit module in the steam network management process includes three parts: key indicators, network overview, and energy flow overview. Based on a general view of a steam network, the key indicator data of the steam network operation is displayed, counted and analyzed in a combination of graphics, text and numbers, to assist a decision-making level in controlling the comprehensive overview, business management and cost-effectiveness of the steam network operation, quickly locate abnormal information of the steam network operation, and scientifically and effectively formulate optimization strategies;

[0064] The monitoring and perception module mainly manages and monitors the pipeline network by classification, grading, role and scenario, and comprehensively perceives the steam supply, transportation, use and loss. Based on the dynamic balance model, it dynamically monitors each steam production and use situation, and comprehensively and dynamically perceives from large to small, from primary to secondary, and from coarse to fine.

[0065] The operation analysis module analyzes the operation data of the pipeline network based on the data of the monitoring perception module and the data output by the algorithm model, combined with the actual management business. It mainly includes consumption analysis, comparative analysis, and abnormal analysis modules. Through the analysis module, it aims to analyze the abnormality, consumption, balance, performance, and cost of the operation process of the pipeline network;

[0066] The auxiliary operation module mainly assists users at the decision-making, management and execution levels to carry out dynamic balance, steady-state adjustment and auxiliary operation of the pipeline network. Its main functions include ensuring steam supply, avoiding excess, analyzing the situation, auxiliary scheduling and terminal control, etc.

[0067] The operation optimization module analyzes excellent operation samples and abnormal operation samples of the pipeline network based on a large amount of historical data and steady-state control sample data, so as to find the direction of pipeline network operation optimization. It combines dynamic data to analyze the current working conditions and provides collaborative optimization operation guidance based on the existing working conditions.

[0068] The knowledge management module includes report management and knowledge sample library management.

[0069] Report management mainly records and extracts important information from each module group to form reports that are important for daily management, such as operation management reports, exception reports, optimization reports, energy efficiency reports, etc. Knowledge sample library management mainly stores and records the valuable data, samples and knowledge information mined by the system in an orderly manner to facilitate the formation of data assets and the inheritance of experience.

[0070] The system management module includes:

[0071] 1) Organization management Organization management is to manage the organizational structure and departments in the system, such as regulating organizational process changes, content changes, etc. Organization management mainly includes functions such as adding, modifying and deleting organizations; 2) User management, manages users and manages permissions according to roles. The background can perform management operations such as user registration, change, and deregistration. User management mainly includes functions such as adding users, associating users with organizations, modifying user information, freezing and unfreezing users; 3) Permission management, manages system permissions according to different user departments and roles; 4) Security management, including menu management, role management, and user log management. Menu management is mainly used to display all function menus of the system; role management mainly includes functions such as adding roles, modifying roles, deleting roles, associating user roles, and authorizing roles; user logs are mainly used to audit user operations; 5) Audit management, mainly audits the operations of system administrators and security administrators; 6) Indicator management, manages process card indicators and performance indicators in the pipeline process, including point changes, formula modifications, and process card indicator boundary modifications.

[0072] The present invention will be further described below in conjunction with the embodiments.

[0073] Embodiment 1:

[0074] (1) Real-time technology path

[0075] Collect data from DCS, SCADA, PIMS, PLC, LIMS and application systems, and complete the construction of multiple business models through five steps: data preprocessing, feature engineering, model building, model evaluation and model deployment. This will achieve super perception of detailed working conditions, process, product performance and key indicators, and thus accurately guide production control.

[0076] (2) Data preprocessing

[0077] The collected historical data will be preprocessed, and data cleaning related algorithms will be used to handle data outliers, data fusion and standardization, which will use technologies such as data cleaning, setting, alignment and standardization.

[0078] (3) Correlation analysis

[0079] The preprocessed and standardized data are subjected to correlation analysis. According to the principle of selecting one of the two variables with strong correlation as the characteristic variable, the preliminary selection of the characteristic variable is realized with the assistance of expert experience.

[0080] Embodiment 2:

[0081] (4) Principal component analysis

[0082] The principal component algorithm is used to extract characteristic variables. For example, if the cumulative variance contribution of the first four principal components is greater than 85%, then it is determined to be four principal components. Each principal component is a linear combination of other indicators, rather than a specific indicator;

[0083] (5) Causal Link Analysis

[0084] Collect all historical data including process, quality, equipment, raw materials, etc., pre-process the data by setting, filtering, standardization, etc., and then use the transfer entropy algorithm to calculate the transfer entropy of the variables related to the model output variables, and draw the causal chain diagram of the model output variables based on the calculation results of the transfer entropy. Then, combine the expert experience from the root cause to screen the characteristic variables;

[0085] Embodiment 3:

[0086] (6) Model construction

[0087] Supply and use data such as steam flow, condensate flow, temperature, pressure, temperature difference, superheat, etc. at each level and each user, with process operation data as input and steam consumption or unit consumption as output to establish a machine learning model. Use the training set part of the historical data to train the model, and combine with genetic algorithms to optimize the model's parameters such as weights and thresholds to complete the model building process;

[0088] (7) Model evaluation

[0089] After the model is built, use the test set part of the historical data to evaluate the model's effectiveness. You can choose prediction accuracy, relative error, and root mean square logarithmic error to evaluate the model. If it meets the business needs, it can be deployed, otherwise the model needs to be rebuilt;

[0090] (8) Model deployment

[0091] When the accuracy of the model meets the business requirements, the model can be deployed. After the model is deployed, it can be connected to online data and perform streaming computing to achieve online calculation and display of indicators such as product quality.

[0092] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0093] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A steam system based on data technology, including a cockpit module, a monitoring perception module, an operation analysis module, an auxiliary operation module, an operation optimization module, a knowledge management module and a system management module in the steam network management process, characterized in that: The cockpit module in the steam network management process includes three parts: key indicators, network overview, and energy flow overview. Based on a steam network overview diagram, the key indicator data of the steam network operation is displayed, counted, and analyzed in a combination of graphics, text, and numbers, to assist a decision-maker in controlling the comprehensive overview, business management, and cost-effectiveness of the steam network operation, quickly locate abnormal information on the steam network operation, and scientifically and effectively formulate optimization strategies; The monitoring and perception module mainly manages and monitors the pipeline network by classification, grading, role and scenario, and comprehensively perceives the steam supply, transportation, use and loss. Based on the dynamic balance model, it dynamically monitors each steam production and use situation, and comprehensively and dynamically perceives from large to small, from primary to secondary, and from coarse to fine. The operation analysis module analyzes the operation data of the pipeline network based on the data of the monitoring perception module and the data output by the algorithm model in combination with the actual management business. It mainly includes consumption analysis, comparative analysis, and abnormality analysis modules. Through the analysis module, it aims to analyze the abnormality, consumption, balance, performance, and cost of the operation process of the pipeline network; The auxiliary operation module mainly assists users at the decision-making, management and execution levels to perform dynamic balance, steady-state adjustment and auxiliary operations of the pipeline network. Its main functions include ensuring steam supply, avoiding excess, analyzing the situation, auxiliary scheduling and terminal control, etc. The operation optimization module analyzes excellent operation samples and abnormal operation samples of the pipeline network based on a large amount of historical data and steady-state control sample data, so as to find the optimization direction of pipeline network operation, analyze the current working conditions in combination with dynamic data, and provide collaborative optimization operation guidance based on the existing working conditions; The knowledge management module includes report management and knowledge sample library management. Report management mainly records and extracts important information from each module group to form reports that are important for daily management, such as operation management reports, exception reports, optimization reports, energy efficiency reports, etc.; the knowledge sample library management mainly stores and records the valuable data, samples and knowledge information mined by the system in an orderly manner to facilitate the formation of data assets and the inheritance of experience.

2. A data-based steam system according to claim 1, characterized in that: The key indicators include the main supply balance indicators of the steam network, energy flow indicators, consumption and loss indicators, unit consumption indicators, abnormal energy consumption and emission indicators; the overall view of the network uses graphic configuration to display the overall view of the first-level network of the whole plant in a macroscopic way, and show the operation status of the main equipment in the first-level network; the overall view of steam energy flow calculates the energy flow based on the materials and process parameters of the steam network, and draws an overall view of the energy flow balance, which can be synchronized with the overall view of the network or switched to display, to assist the decision-making layer to quickly grasp the operation information of the network.

3. A steam system based on data technology according to claim 2, characterized in that: The monitoring perception module includes: 1) Supply situation monitoring Monitor all supply points in the pipe network and the main process parameters that affect supply, such as the amount of coal used by the boiler, the air volume, etc., the data related to the operation of the process waste heat boiler, the heat load, the heat exchange temperature and other parameters. At the same time, various charts such as trend charts are used for auxiliary display; 2) Pipeline network equipment Pipeline network equipment monitoring mainly monitors the parameters of pipeline network equipment such as desuperheaters, pressure reducers, desuperheating and pressure reducing devices, vent valves, distribution tables, flash tanks, condensers, etc. Capture the most core data for monitoring, such as valve position, water replenishment volume, delivery volume, condensing temperature, etc. 3) Steam turbine operation status Focus on monitoring the operation of the steam turbine. The main monitoring indicators include core indicators such as steam consumption, extraction volume, standby pressure, condensate volume, power generation or channel equipment load, as well as temperature, temperature difference, superheat, pressure, effective work, enthalpy value, etc. during operation; 4) Pipeline network usage It is mainly for users other than power steam users in the pipeline network. According to the situation of on-site sensors, the device, section, or even specific equipment can be used as the monitoring object. The main monitoring indicators include pressure, pressure difference, temperature, temperature difference, flow, superheat, dryness, etc. 5) Pipeline network loss Based on the dynamic balance model of the pipeline network, the system dynamically analyzes the loss of five levels of pipeline networks, such as steam material loss and energy loss, down to the user point. It issues an alarm for deviations or large losses; 6) Abnormality warning Abnormal alarm warning is mainly based on dynamic balance model and steady-state model, drawing dynamic multi-parameter and single-parameter steady-state control base and dynamic reference curve. Based on this, real-time dynamic and actual working conditions are compared and analyzed, and single or multiple parameters that deviate from the steady-state value are warned to assist in the adjustment and control of indicators.

4. A data-based steam system according to claim 3, characterized in that: The operation analysis module comprises: 1) Consumption analysis This module mainly analyzes the overall steam consumption of the steam network, the steam consumption of the five-level network, the steam consumption of each user point, and the condensate loss. The analysis includes trend analysis, proportion analysis, component analysis, and unit consumption analysis. 2) Abnormal analysis Abnormal analysis mainly determines the warning items based on the monitoring and early warning module, analyzes the abnormal items, such as the correlation of abnormal indicators, main causes, and causal links, and records the abnormal indicators and corresponding working conditions to form abnormal analysis reports, and automatically accumulates negative sample data as the iteration basis of the steady-state model to assist in the adjustment and control of indicators; 3) Feature analysis The main cause analysis and causal link determination are carried out for the performance data, abnormal data and optimization data in the operation of the pipeline network, and the influencing factors of the core data are dynamically displayed. The data concerned by the user and the related features can be queried and visualized; 4) Balance analysis According to the actual business, the overall pipeline network is dynamically balanced, with energy balance as the main factor and materials as the auxiliary factor. Balance analysis is also conducted on the five levels and major users. The overall pipeline network operation is included in the dynamic balance system, and the balance results are dynamically analyzed; 5) Energy flow analysis Conduct energy flow analysis and energy efficiency analysis on the five-level pipeline network and each user point, display the analysis results, conduct rationality analysis on energy flow changes, and conduct statistics and analysis on parameters with large deviations and abnormal energy flow fluctuations. Pay attention to its change range, impact area, and macroscopic impact on upper and lower level steam, etc.; 6) Pre-alarm analysis This module mainly analyzes alarm and warning indicators, such as alarm frequency, area, attributes, etc., in order to provide decision-making basis for subsequent adjustments and improvements; 7) Performance Analysis This module mainly conducts statistical analysis on the main management and control performance indicators, with a frequency of no more than 1 hour / time. The analysis results are presented, and comparative analysis is conducted in the form of team rankings, daily statistics, and weekly statistics. In combination with historical operation conditions, comprehensive and continuous analysis and evaluation are conducted; 8) Comprehensive cost analysis This module mainly analyzes the steam cost allocated to each user point based on the performance analysis results, and combines the steady-state operation part of historical data as a benchmark, providing standards and basis for current cost control.

5. A data-based steam system according to claim 4, characterized in that: The auxiliary operation module comprises: 1) Steam supply guarantee Steam supply is guaranteed based on dynamic balance and demand forecast, and five levels of steam control parameters are operated to ensure supply, such as adjusting steam pressure, temperature, flow, energy, and the use of temperature and pressure reducers; 2) Excess steam Steam oversupply prevention is based on dynamic balance and demand forecasting, and pre-adjusts the five levels of steam control parameters to prevent abnormal steam network venting, abnormal use of temperature and pressure reducers, abnormal fluctuations in steam extraction, and reduced steam heat exchange efficiency due to excess material and energy supply; 3) Situation prediction This module is mainly based on a forecasting model with multiple algorithms and multi-dimensional forecasting. It combines the actual supply, demand and consumption data and dynamic balance to predict the changing trend of the supply and demand side, and macroscopically control the changing situation of the overall pipeline network. At the same time, it classifies and classifies the changing trend of each gas consumption end, focusing on presenting the most important factors affecting the balance of the pipeline network. 4) Scheduling analysis Through the data from the above-mentioned monitoring, early warning, analysis and situation prediction modules, a macro-situation change graph of the pipeline network is formed to assist in dispatching and allocating steam balance to maintain the steady-state operation of the pipeline network; 5) Terminal Control Conduct data analysis on multiple user ends and control ends, analyze abnormal operation fluctuations and abnormal gas usage, such as energy consumption analysis, energy efficiency analysis, and trend analysis, and provide operation strategies for optimization, maintenance, and degradation improvement.

6. A data-based steam system according to claim 5, characterized in that: The operation optimization module comprises: 1) Control optimization, auxiliary dispatch, and auxiliary adjustment of the macro operation of the pipeline network, such as overall energy consumption, energy efficiency, material consumption, condensate recovery and other plant-level macro control assistance; 2) Balance optimization, based on the prediction and steady-state operation model, to achieve dynamic balance optimization of the overall pipeline network. If the prediction model has the possibility of emptying, make adjustments on the supply side in advance, and combine the needs of terminal and pipeline network optimization to form a synergistic balance optimization; 3) Supply optimization, supply-side optimization, is to adjust to the optimal supply under the premise of ensuring steam supply, such as gradually increasing the supply load to the precise load according to the characteristics of the dynamic changes of the pipeline network. The system will work together It provides time control and target control parameters to assist in supply optimization; 4) Terminal optimization: The user end has many users and large fluctuations, making it difficult to accurately control. Assisted terminal tuning is based on the terminal's operating data. Under the premise of ensuring the overall network stability, adjustments are made to terminal users. The optimization directions are mainly gas volume, temperature, pressure, and effective steam work; 5) Performance evaluation: It mainly evaluates the performance before and after collaborative optimization, evaluates the current performance, and performs trend analysis on the results, displays excellent and poor situations, and ranks the overall performance of the team.

7. A data-based steam system according to claim 6, characterized in that: The system management module includes: 1) Organization management Organization management is to manage the organizational structure and departments in the system, such as regulating organizational process changes, content changes, etc. Organization management mainly includes functions such as adding, modifying and deleting organizations; 2) User management, manages users and manages permissions according to roles. The background can perform management operations such as user registration, change, and deregistration. User management mainly includes functions such as adding users, associating users with organizations, modifying user information, freezing and unfreezing users; 3) Permission management, manages system permissions according to different user departments and roles; 4) Security management, including menu management, role management, and user log management. Menu management is mainly used to display all function menus of the system; role management mainly includes functions such as adding roles, modifying roles, deleting roles, associating user roles, and authorizing roles; user logs are mainly used to audit user operations; 5) Audit management, mainly audits the operations of system administrators and security administrators; 6) Indicator management, manages process card indicators and performance indicators in the pipeline process, including point changes, formula modifications, and process card indicator boundary modifications.

8. A data-based steam system according to claim 7, characterized in that: Implementation steps include: 1) Real-time technology path Collect data from DCS, SCADA, PIMS, PLC, LIMS and application systems, and complete the construction of multiple business models through five steps: data preprocessing, feature engineering, model building, model evaluation and model deployment, so as to achieve super perception of subdivided working conditions, process, product performance and key indicators, and then accurately guide production control; 2) Data preprocessing The collected historical data will be preprocessed, and data cleaning related algorithms will be used to handle data outliers, data fusion and standardization, which will use technologies such as data cleaning, setting, alignment and standardization.

9. A data-based steam system according to claim 8, characterized in that: The system is divided into three layers: the first is the data layer, including data collection and database establishment; the second is the model layer, which realizes online monitoring, online simulation and maintenance functions; the third is the result display layer, that is, the application layer, which is used for enterprise management and operators, and has statistical reports, system monitoring and system optimization.

10. A steam system based on data technology according to claim 9, characterized in that: The data interface is connected to the enterprise database to realize the online intelligent optimization operation of the steam power system of the whole plant and improve the working efficiency of the steam system.

Images