Steam-injection boiler collaborative scheduling method and device based on multi-event state, electronic equipment and storage medium

Abstract

The invention relates to the technical field of steam-injection boiler operation and maintenance, in particular to a steam-injection boiler collaborative scheduling method and device based on multiple event states, electronic equipment and a storage medium. The method comprises the steps that a corresponding operation event portrait is extracted from scheduling basic information of a boiler to be scheduled; necessary scheduling information is extracted from the operation event portrait of the boiler to be scheduled and input into the static collaborative optimization model, weekly planned scheduling of the boiler to be scheduled is obtained, and the static collaborative optimization model is used for solving the target function through an optimization algorithm when constraint conditions needed by scheduling are met. According to the method, a large amount of different source data of the boiler is integrated and analyzed, the operation event portrait of the boiler is extracted, the target function is determined based on management between the scheduling and the operation event portrait, the target function is solved by using the optimization algorithm, the weekly plan scheduling is obtained, the scheduling efficiency is improved, the scheduling accuracy is ensured, and the scheduling efficiency is improved. And a good support is provided for stable operation of production.

Description

Technical Field

[0001] This invention relates to the field of steam injection boiler operation and maintenance technology, and is a method, device, electronic device and storage medium for collaborative scheduling of steam injection boilers based on multi-event states. Background Technology

[0002] Heavy oil fields account for a significant proportion of the world's proven oil fields. The heavy oil steam huff and puff process is relatively simple, quick to produce results, and mature due to its long history of use. It does not require extensive testing during the extraction process, allowing for simultaneous production and research at the well, and is therefore widely used.

[0003] Heavy oil steam injection requires the rational and efficient use of steam injection boilers to generate steam, which is then injected into heavy oil wells through steam pipelines. The operation and management of steam injection boilers and energy-saving optimization, the selection and combination optimization of wells to be rolled, and the optimization of steam distribution to heavy oil wells all affect the optimization of steam injection costs. Especially in the middle and late stages of heavy oil block development, the steam injection cycle becomes longer, the cycle production effect deteriorates, and the problems of low oil-steam ratio, high energy consumption, and low efficiency become increasingly serious; the steam injection cost is high, and there is great potential for optimization.

[0004] The following problems exist with steam injection:

[0005] (1) Manual boiler scheduling is difficult to meet the needs of further improvement: Through IoT monitoring and management assessment, the current steam qualification rate has reached a high level. Further improvement is focused on cross-link collaboration between geological turbine and boiler steam injection, boiler operation and maintenance and steam injection production needs, boiler on-site operation and boiler planning management, etc., which requires the integration and processing of a large amount of data from different sources, far exceeding the capacity of manual processing.

[0006] (2) High cost of manual coordination between heavy oil well runner and heat injection management: Currently, the geology proposes a runner plan from the perspective of production. After coordination between the heat injection management center and the production site, modification suggestions are formed. Through manual coordination, the daily steam injection plan and boiler schedule of heavy oil well are finally formed, which is inefficient.

[0007] Existing publicly available patent literature, publication number CN117273404B, discloses an automatic boiler scheduling method based on big data analysis. This method includes: acquiring multiple sets of boiler information to train a heuristic optimization algorithm model; establishing a digital twin virtual model of the boiler, which can predict the remaining lifespan of boiler components based on boiler parameter information; feeding the results of the digital twin virtual model back to the iterative process of the heuristic optimization algorithm model, and calculating the boiler scheduling by combining the fitness function and preset constraints. This patent disclosure considers that when maximizing boiler efficiency, the non-smooth nature of the optimal solution can easily lead to fatigue or even damage to some components in the boiler. This invention creatively uses a digital twin virtual model to evaluate the results of each iteration in the particle swarm optimization algorithm, thereby controlling the convergence speed and weight factors of the particle swarm optimization algorithm.

[0008] While the aforementioned existing patents also involve automatic boiler scheduling based on big data analysis, they utilize boiler information, including parameter information and status information (parameter information may include boiler output thermal power, feedwater flow rate, boiler temperature, air flow rate, boiler steam pressure, etc., and status information may include steam mass flow rate, steam outlet enthalpy and inlet enthalpy, fuel mass flow rate, fuel calorific value, etc.) to predict the remaining lifespan of boiler components. This information is then combined with an optimization algorithm model to complete boiler scheduling. The data used is relatively simple and does not involve integrating and analyzing a large amount of different sources of boiler data to extract events for scheduling. Summary of the Invention

[0009] This invention provides a method, apparatus, electronic device, and storage medium for collaborative scheduling of steam injection boilers based on multi-event states, which overcomes the shortcomings of the prior art and can effectively solve the problems of low efficiency and inability to integrate and process large amounts of data in existing manual scheduling.

[0010] One of the technical solutions of this invention is achieved through the following measures: a collaborative scheduling method for steam injection boilers based on multi-event states, comprising:

[0011] Extract the corresponding operation event profile from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operation event profile includes the event, future operation and maintenance requirements, and the health status of the boiler.

[0012] Essential scheduling information is extracted from the operational event profile of the boiler to be scheduled and input into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The essential scheduling information extracted includes abnormal events, operational behaviors and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function when the constraints required for scheduling are met to obtain the weekly schedule.

[0013] The following are further optimizations and / or improvements to the above-mentioned technical solution:

[0014] The above also includes simulating the weekly schedule of the boiler to be scheduled, and readjusting the weekly schedule when the simulation results are unsatisfactory.

[0015] The above-mentioned simulation of the weekly scheduling of the boiler to be scheduled, and the readjustment of the weekly scheduling when the simulation results are unsatisfactory, includes:

[0016] For the weekly scheduling of boilers to be scheduled, obtain the remaining duration and risk level of each event in the weekly scheduling;

[0017] Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, the Monte Carlo simulation method is used to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and the boiler gas supply performance is obtained through simulation.

[0018] Analyze the gas supply performance of the boiler to determine whether the gas supply performance is up to standard.

[0019] In response to unsatisfactory boiler gas supply performance, the weekly schedule of the boilers to be scheduled will be readjusted. The readjustment methods include manual modification and adjustment of the parameters of the static collaborative optimization model.

[0020] The objective function and constraints in the above static collaborative optimization model are as follows:

[0021]

[0022] st

[0023] The daily steam injection capacity meets the steam injection demand. 24-hour daily restriction;

[0024] The time required for handling exceptions is related to whether the handling is done earlier or later.

[0025] The requirements stipulated by regulations must be completed before the regulatory deadline;

[0026] Among them, I w The design injection intensity for the well to be injected (w) is the daily steam injection rate; V t F represents the estimated steam injection volume of the well already injected on day t; t To determine whether steam injection was completed at any betting well on day t; C b The daily steam production capacity of boiler b; The time required to eliminate the abnormal event e by adopting preventive measures; The time required to eliminate the abnormal event e using responsive processing; The expected failure days for abnormal event e; The deadline for boiler type r as required by regulations b; The time required for processing type r as required by regulations; Let N be the planned time that boiler b has been occupied on day t; D is the planned duration; w The number of days until well w is started to be injected; The steam injection duration on the first day of the well to be injected; For boiler B, the handling of abnormalities is required on this day; For boiler b, the response day to regulation r; Let t be the working hours of boiler b in day t; The abnormal handling time for boiler b on day t is denoted as .

[0027] The above-mentioned process extracts the corresponding operational event profiles from the basic scheduling information of the boilers to be scheduled, including:

[0028] Obtain the basic scheduling information of the boiler to be scheduled, including the turbine runner plan, daily injection reports, boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts.

[0029] The basic scheduling information of the boilers to be scheduled is input into the operation event extraction engine to extract the corresponding operation event profile. The operation event extraction engine is obtained by training the word segmentation engine and cluster analysis algorithm using the historical scheduling information of several boilers.

[0030] The construction process of the above-mentioned event extraction engine includes:

[0031] Obtain basic historical scheduling information for several boilers, including turbine runner schedules, daily injection reports, boiler maintenance plans, and a set of abnormal events that have occurred in the boilers and their impacts.

[0032] The basic information of the historical scheduling of several boilers was segmented using a word segmentation engine, and a domain dictionary was constructed based on frequency statistics.

[0033] Commonly used phrase patterns are discovered from frequency statistics results, and a set of regular expressions is constructed based on these phrase patterns to form a phrase pattern library.

[0034] Cluster analysis was performed on the discovered phrase patterns, and the typical event types in the boiler operation process were summarized based on the clustering results to form a boiler operation event classification tree.

[0035] The second technical solution of the present invention is achieved through the following measures: a multi-event state-based steam injection boiler coordinated scheduling device, comprising:

[0036] The profiling unit extracts the corresponding operational event profiles from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operational event profiles include the events, future operation and maintenance requirements, and the health status of the boiler.

[0037] The scheduling unit extracts necessary scheduling information from the operational event profile of the boiler to be scheduled and inputs it into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The necessary scheduling information extracted includes abnormal events, operational behaviors, and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function while meeting the constraints required for scheduling to obtain the weekly schedule.

[0038] The following are further optimizations and / or improvements to the above-mentioned technical solution:

[0039] The aforementioned evaluation unit simulates the weekly schedule of the boiler to be scheduled, and readjusts the weekly schedule when the simulation results are unsatisfactory, including:

[0040] For the weekly scheduling of boilers to be scheduled, obtain the remaining duration and risk level of each event in the weekly scheduling;

[0041] Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, the Monte Carlo simulation method is used to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and the boiler gas supply performance is obtained through simulation.

[0042] Analyze the gas supply performance of the boiler to determine whether the gas supply performance is up to standard.

[0043] In response to unsatisfactory boiler gas supply performance, the weekly schedule of the boilers to be scheduled will be readjusted. The readjustment methods include manual modification and adjustment of the parameters of the static collaborative optimization model.

[0044] The third technical solution of the present invention is achieved through the following measures: a storage medium storing a computer program that can be read by a computer, the computer program being configured to execute a collaborative scheduling method for steam injection boilers based on multiple event states during runtime.

[0045] The fourth technical solution of the present invention is achieved through the following measures: an electronic device, including a processor and a memory, wherein the memory stores a computer program, which is loaded and executed by the processor to implement a collaborative scheduling method for steam injection boilers based on multiple event states.

[0046] This invention transforms traditional manual boiler scheduling into automatic boiler scheduling. It integrates and analyzes a large amount of boiler data from different sources, extracts operational event profiles, and determines an objective function based on the management relationship between the scheduling and the operational event profiles. An optimization algorithm is then used to solve the objective function to obtain the weekly schedule, which improves scheduling efficiency and ensures scheduling accuracy, providing strong support for stable production operation. Furthermore, this invention uses Monte Carlo simulation to simulate each event in the weekly schedule, thereby verifying the validity of the weekly schedule and readjusting any unqualified weekly schedules, thus improving scheduling accuracy. Attached Figure Description

[0047] Appendix Figure 1 This is a schematic diagram illustrating the implementation environment of the present invention.

[0048] Appendix Figure 2 This is a schematic diagram of a scheduling method according to the present invention.

[0049] Appendix Figure 3 This is a schematic diagram of the method for extracting runtime event profiles in this invention.

[0050] Appendix Figure 4 This is a schematic diagram of the structure of the event extraction engine in this invention.

[0051] Appendix Figure 5 This is a schematic diagram of the construction method of the event extraction engine in this invention.

[0052] Appendix Figure 6 This is a schematic diagram of another scheduling method according to the present invention.

[0053] Appendix Figure 7 This is a schematic diagram of the method for simulating the weekly scheduling of the boiler to be scheduled in this invention.

[0054] Appendix Figure 8 This is a schematic diagram of the device structure of the present invention. Detailed Implementation

[0055] The present invention is not limited to the following embodiments, and the specific implementation can be determined according to the technical solution of the present invention and the actual situation.

[0056] Those skilled in the art will understand that, unless otherwise stated, in the embodiments of this application, "module" or "unit" refers to a computer program or part of a computer program with a predetermined function, which works together with other related parts to achieve a predetermined goal, and can be implemented, wholly or partially, using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0057] In addition, in the embodiments of this application, "multiple" refers to two or more, and "first" and "second" are used to distinguish descriptions and should not be construed as implying relative importance.

[0058] The architecture of the collaborative scheduling system for steam injection boilers based on multi-event states provided in the embodiments of this application is described below.

[0059] This application provides a method, apparatus, electronic device, and storage medium for collaborative scheduling of steam injection boilers based on multiple event states. The apparatus for collaborative scheduling of steam injection boilers based on multiple event states can be integrated into a computer device, which can be a server or a terminal, etc. It is understood that the collaborative scheduling method for steam injection boilers based on multiple event states in this embodiment can be executed on a server, on a terminal, or jointly by a terminal and a server; the above examples should not be construed as limiting this application.

[0060] like Figure 1 As shown, the example illustrates a collaborative scheduling method for steam injection boilers based on multiple event states, executed jointly by a terminal and a server. The collaborative scheduling system for steam injection boilers based on multiple event states provided in this application includes a terminal and a server; the terminal and server are connected via a network, which can be a wired network or a wireless network, etc. The collaborative scheduling device for steam injection boilers based on multiple event states can be integrated into the terminal.

[0061] The terminal provides an interactive interface for a multi-event state-based collaborative scheduling method for steam injection boilers. This interface allows users to acquire various information, including basic scheduling information and parameter configuration information for the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, daily injection reports, boiler maintenance plans, and a set of abnormal events that have occurred and their impacts. The parameter configuration information includes execution event profiles and various parameter configurations from the static collaborative optimization model. Furthermore, the terminal provides an interface for displaying, viewing, and modifying the scheduling data. After obtaining the rejection simulation results, users can manually modify the scheduling and view historical scheduling data based on permission settings. The terminal can include mobile phones, wearable smart devices, tablets, laptops, personal computers (PCs), and in-vehicle computers, etc., and this application does not limit the number of terminal devices.

[0062] The server provides various data processing and analysis processes in the collaborative scheduling method for steam injection boilers based on multi-event states. Specifically, it can extract corresponding operational event profiles based on the basic scheduling information of the boiler to be scheduled. After extracting the operational event profiles, it extracts necessary scheduling information from the operational event profiles of the boiler to be scheduled and inputs them into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. It can also simulate the weekly schedule of the boiler to be scheduled. The construction process of the static collaborative optimization model can also be completed in the server. The server here can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This application does not impose any restrictions on this.

[0063] The present invention will be further described below with reference to embodiments and accompanying drawings:

[0064] Example 1: As shown in the attached document Figure 2 As shown, this embodiment of the invention discloses a collaborative scheduling method for steam injection boilers based on multi-event states, including:

[0065] Step S110: Extract the corresponding operation event profile from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operation event profile includes the event, future operation and maintenance requirements, and the health status of the boiler.

[0066] In this embodiment, data support is provided for scheduling by creating a profile of the operating events of the boiler to be scheduled based on the basic scheduling information of the boiler to be scheduled.

[0067] The basic scheduling information includes the well runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The well runner plan includes the expected end date of injection, the well to be runnered, and the expected injection volume. The daily injection report includes the injection progress. The boiler maintenance plan includes the boiler's full life cycle maintenance plan, such as the first maintenance and annual inspection. The set of abnormal events that have occurred in the boiler and their impacts is obtained through the duty log.

[0068] The operational event profile includes events, future maintenance requirements, and the boiler's health status. Events are obtained through a set analysis of abnormal events that have occurred in the boiler and their impacts; future maintenance requirements are obtained by integrating the boiler's maintenance plan; and the boiler's health status is obtained through a comprehensive analysis of the runner schedule and daily injection reports.

[0069] Step S120: Extract necessary scheduling information from the operation event profile of the boiler to be scheduled and input it into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The necessary scheduling information extracted includes abnormal events, operation behaviors and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function when the constraints required for scheduling are met to obtain the weekly schedule.

[0070] In this embodiment, the static collaborative optimization model uses an optimization algorithm to solve the objective function to obtain the weekly schedule when the constraints required for scheduling are met. The core logic of the static collaborative optimization model in executing the schedule is to perform flushing and other inspection work as much as possible at the time when the well injection is completed (to reduce the impact on the wells being injected and to ensure the continuity of the wells to be injected) without causing significant risks. If the remaining time of the abnormal event cannot support the completion of the well injection, a time period in which the steam supply capacity can meet the requirements is found, and the wells to be injected are put into operation as soon as possible, provided that the heating station capacity is sufficient.

[0071] In this embodiment, the objective function of the static collaborative optimization model takes as input the necessary scheduling information extracted from the operational event profile of the boiler to be scheduled, and outputs the number of days for boiler to handle anomalies, the number of days for boiler to respond to regulations, the number of days for wells to be put into operation, and the steam injection duration on the first day of wells to be injected. The objective function is constructed based on the relationship between the input and output, and the constraints can be set according to indicators such as production requirements, steam injection qualification rate, improving the continuity of the next round of steam injection, boiler reliability (remaining time for different abnormal events), compliance regulations (statutory maintenance), and operating procedures (steam injection pressure).

[0072] In this embodiment, the weekly schedule output by the static collaborative optimization model includes the arrangement of steam injection, anomaly investigation, or maintenance for a single boiler within a week.

[0073] The multi-event state-based collaborative scheduling method for steam injection boilers provided in this embodiment transforms traditional manual boiler scheduling into automatic boiler scheduling. It integrates and analyzes a large amount of data from different sources of boilers, extracts boiler operation event profiles, and determines the objective function based on the management relationship between scheduling and operation event profiles. The objective function is then solved using an optimization algorithm to obtain the weekly schedule, which improves scheduling efficiency and ensures scheduling accuracy, providing good support for stable production operation.

[0074] Example 2: As shown in the attached document Figure 3 As shown, the specific implementation method for step S110, which involves extracting the corresponding operational event profile from the basic scheduling information of the boiler to be scheduled, includes:

[0075] Step S210: Obtain the basic scheduling information of the boiler to be scheduled, including the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts.

[0076] Specifically, the well runner plan includes the expected end date of well injection, the well to be runner, and the expected gas injection volume. The well injection daily report includes the well injection progress. The boiler maintenance plan includes the boiler's full life cycle maintenance plan, such as the first maintenance and annual inspection. The collection of abnormal events that have occurred in the boiler and their impacts is obtained through the duty log.

[0077] Step S220: Input the basic scheduling information of the boiler to be scheduled into the operation event extraction engine to extract the corresponding operation event profile. The operation event extraction engine is obtained by training the word segmentation engine and clustering analysis algorithm using the historical scheduling information of several boilers.

[0078] For details, see attached. Figure 4 , 5 As shown, the construction process of running the event extraction engine includes:

[0079] Step S221: Obtain basic historical scheduling information for several boilers, including turbine runner schedules, daily injection reports, boiler maintenance schedules, and a set of abnormal events that have occurred in the boilers and their impacts.

[0080] Step S222: Use a word segmentation engine to segment the historical scheduling basic information of several boilers, and construct a domain dictionary based on frequency statistics;

[0081] Step S223: Discover common phrase patterns in the frequency statistics results, construct a set of regular expressions based on the phrase patterns, and form a phrase pattern library;

[0082] Step S224: Perform cluster analysis on the discovered phrase patterns, summarize and generalize the typical event types in the boiler operation process based on the clustering results, and form a boiler operation event classification tree.

[0083] Steps S222 to S224 above constitute the process of offline training and modeling using basic historical scheduling information from several boilers. Specifically, refer to the appendix... Figure 4 The analysis engine is used to segment the basic historical scheduling information of several boilers, and synonyms are organized based on frequency statistics to build and update a domain dictionary, thereby training an accurate segmentation engine. Based on frequency statistics, common phrase patterns are extracted and regular expressions are introduced. A phrase pattern library is formed by organizing the corresponding regular expressions according to common phrase patterns. A clustering analysis algorithm is introduced to perform cluster analysis on the organized common phrase patterns to obtain typical event types in the boiler operation process and form event classification numbers. Typical event types include boiler status (such as boiler start-up, shutdown, standby status, etc.), boiler actions (such as operating condition adjustments, etc.), planned shutdowns (such as annual inspections, major overhauls, etc.), unplanned shutdowns (such as hardware and software failures of the boiler system, etc.), and shutdowns due to external influences (boiler shutdowns caused by failures in other systems, etc.). The corresponding typical event classification table is shown below:

[0084] Table 1 Classification of Boiler Operation Events

[0085]

[0086] Specifically, step S220 inputs the basic scheduling information of the boiler to be scheduled into the operation event extraction engine. The specific process of extracting the operation event profile includes: inputting the basic scheduling information of the boiler to be scheduled into the word segmentation engine for word segmentation, extracting common phrases using regular expressions in the phrase pattern library after word segmentation, and determining the operation event profile based on the event classification tree of the common phrase set.

[0087] Example 3: The objective function and constraints in the static collaborative optimization model in step S120 are as follows:

[0088]

[0089] st

[0090] The daily steam injection capacity meets the steam injection demand.

[0091] 24-hour daily restriction;

[0093] The time required for handling exceptions is related to whether the handling is done earlier or later.

[0094] The requirements stipulated by regulations must be completed before the regulatory deadline;

[0095] The explanations of all parameters in the objective function and constraints are shown in Table 2.

[0096] Table 2 Parameter Description

[0097]

[0098]

[0099] Example 4: As shown in the appendix Figure 6 As shown, this embodiment of the invention discloses a collaborative scheduling method for steam injection boilers based on multi-event states, including:

[0100] Step S310: Extract the corresponding operation event profile from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operation event profile includes the event, future operation and maintenance requirements, and the health status of the boiler.

[0101] Step S320: Extract necessary scheduling information from the operation event profile of the boiler to be scheduled and input it into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The necessary scheduling information extracted includes abnormal events, operation behaviors and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function when the constraints required for scheduling are met to obtain the weekly schedule.

[0102] Step S330: Simulate the weekly schedule of the boiler to be scheduled, and readjust the weekly schedule if the simulation results are unsatisfactory.

[0103] The above step S330 is as follows: Figure 7 As shown, it specifically includes:

[0104] Step S331: For the weekly schedule of the boiler to be scheduled, obtain the remaining duration and risk level of each event in the weekly schedule.

[0105] Step S332: Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, use the Monte Carlo simulation method to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and simulate the boiler gas supply performance.

[0106] Step S333: Analyze the gas supply performance of the boiler to determine whether the boiler gas supply performance is qualified; the gas supply indicators here may include, but are not limited to, continuous steam supply satisfaction rate, steam supply qualification rate, etc.

[0107] Step S334: In response to the boiler's gas supply performance being unqualified, the weekly schedule of the boiler to be scheduled is readjusted. The readjustment method includes manual modification and adjustment of the parameters of the static collaborative optimization model.

[0108] In this embodiment, the Monte Carlo simulation method is used to simulate each event in the weekly schedule, thereby verifying whether the weekly schedule is qualified and readjusting unqualified weekly schedules, thereby further improving the accuracy of the schedule. The Monte Carlo simulation method is an existing technology and will not be described in detail. The Monte Carlo simulation method can be executed by MATLAB.

[0109] In this embodiment, before performing the simulation, it is necessary to obtain the remaining duration and risk level of each event in the weekly schedule. This can be achieved, but is not limited to, using Hazard probability methods such as COX to express the likelihood that different event risks will cause a furnace shutdown or require intervention on each day. The remaining duration and risk level of different event types in this embodiment are shown in the table below:

[0110] Table 3. Remaining Duration and Risk Level for Different Event Types

[0111]

[0112]

[0113] Example 5: As shown in the attached document Figure 8 As shown, this embodiment of the invention discloses a collaborative scheduling device for steam injection boilers based on multi-event states, comprising:

[0114] The profiling unit extracts the corresponding operational event profiles from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operational event profiles include the events, future operation and maintenance requirements, and the health status of the boiler.

[0115] The scheduling unit extracts necessary scheduling information from the operation event profile of the boiler to be scheduled and inputs it into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The necessary scheduling information extracted includes abnormal events, operation behaviors and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function when the constraints required for scheduling are met to obtain the weekly schedule.

[0116] The evaluation unit simulates the weekly schedule of the boiler to be scheduled, and readjusts the weekly schedule if the simulation results are unsatisfactory. This includes:

[0117] For the weekly scheduling of boilers to be scheduled, obtain the remaining duration and risk level of each event in the weekly scheduling;

[0118] Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, the Monte Carlo simulation method is used to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and the boiler gas supply performance is obtained through simulation.

[0119] Analyze the gas supply performance of the boiler to determine whether the gas supply performance is up to standard.

[0120] In response to unsatisfactory boiler gas supply performance, the weekly schedule of the boilers to be scheduled will be readjusted. The readjustment methods include manual modification and adjustment of the parameters of the static collaborative optimization model.

[0121] Example 6: This embodiment of the invention discloses a storage medium storing a computer program that can be read by a computer. The computer program is configured to execute a collaborative scheduling method for steam injection boilers based on multiple event states during runtime.

[0122] The aforementioned storage media may include, but are not limited to, USB flash drives, read-only memory, portable hard drives, magnetic disks, optical disks, and other media capable of storing computer programs.

[0123] Example 7: This embodiment of the invention discloses an electronic device, including a processor and a memory. The memory stores a computer program, which is loaded and executed by the processor to implement a collaborative scheduling method for steam injection boilers based on multiple event states.

[0124] The processor described above can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. It can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The memory can include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, portable hard drives, magnetic disks, or optical disks.

[0125] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0126] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] The above technical features constitute the preferred embodiment of the present invention, which has strong adaptability and optimal implementation effect. Unnecessary technical features can be added or removed according to actual needs to meet the requirements of different situations.

Claims

1. A collaborative scheduling method for steam injection boilers based on multi-event states, characterized in that, include: Extract the corresponding operation event profile from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operation event profile includes the event, future operation and maintenance requirements, and the health status of the boiler. Essential scheduling information is extracted from the operational event profile of the boiler to be scheduled and input into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The essential scheduling information extracted includes abnormal events, operational behaviors and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function when the constraints required for scheduling are met to obtain the weekly schedule.

2. The collaborative scheduling method for steam injection boilers based on multi-event states according to claim 1, characterized in that, It also includes simulating the weekly schedule of the boiler to be scheduled, and readjusting the weekly schedule when the simulation results are unsatisfactory.

3. The collaborative scheduling method for steam injection boilers based on multi-event states according to claim 2, characterized in that, The simulation of the weekly schedule for the boiler to be scheduled, and the readjustment of the weekly schedule when the simulation results are unsatisfactory, includes: For the weekly scheduling of boilers to be scheduled, obtain the remaining duration and risk level of each event in the weekly scheduling; Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, the Monte Carlo simulation method is used to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and the boiler gas supply performance is obtained through simulation. Analyze the gas supply performance of the boiler to determine whether the gas supply performance is up to standard. In response to unsatisfactory boiler gas supply performance, the weekly schedule of the boilers to be scheduled will be readjusted. The readjustment methods include manual modification and adjustment of the parameters of the static collaborative optimization model.

4. The method for collaborative scheduling of steam injection boilers based on multi-event states according to claim 1, 2, or 3, characterized in that, The objective function and constraints in the static collaborative optimization model are as follows: st The daily steam injection capacity meets the steam injection demand. 24-hour daily restriction; The time required for handling exceptions is related to whether the handling is done earlier or later. The requirements stipulated by regulations must be completed before the regulatory deadline; Among them, I w The design injection intensity for the well to be injected (w) is the daily steam injection rate; V t F represents the estimated steam injection volume of the well already injected on day t; t To determine whether steam injection was completed at any betting well on day t; C b The daily steam production capacity of boiler b; The time required to eliminate the abnormal event e by adopting preventive measures; The time required to eliminate the abnormal event e using responsive processing; The expected failure days for abnormal event e; The deadline for boiler type r as required by regulations b; The time required for processing type r as required by regulations; Let N be the planned time that boiler b has been occupied on day t; D is the planned duration; w The number of days until well w is started to be injected; The steam injection duration on the first day of the well to be injected; For boiler B, the handling of abnormalities is required on this day; For boiler b, the response day to regulation r; Let t be the working hours of boiler b in day t; The abnormal handling time for boiler b on day t is denoted as .

5. The method for collaborative scheduling of steam injection boilers based on multi-event states according to any one of claims 1 to 4, characterized in that, The step of extracting the corresponding operational event profile from the basic scheduling information of the boiler to be scheduled includes: Obtain the basic scheduling information of the boiler to be scheduled, including the turbine runner plan, daily injection reports, boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The basic scheduling information of the boilers to be scheduled is input into the operation event extraction engine to extract the corresponding operation event profile. The operation event extraction engine is obtained by training the word segmentation engine and cluster analysis algorithm using the historical scheduling information of several boilers.

6. The collaborative scheduling method for steam injection boilers based on multi-event states according to claim 5, characterized in that, The construction process of the runtime event extraction engine includes: Obtain basic historical scheduling information for several boilers, including turbine runner schedules, daily injection reports, boiler maintenance plans, and a set of abnormal events that have occurred in the boilers and their impacts. The basic information of the historical scheduling of several boilers was segmented using a word segmentation engine, and a domain dictionary was constructed based on frequency statistics. Commonly used phrase patterns are discovered from frequency statistics results, and a set of regular expressions is constructed based on these phrase patterns to form a phrase pattern library. Cluster analysis was performed on the discovered phrase patterns, and the typical event types in the boiler operation process were summarized based on the clustering results to form a boiler operation event classification tree.

7. A multi-event state-based steam injection boiler collaborative scheduling device applying the method described in any one of claims 1 to 6, characterized in that, include: The profiling unit extracts the corresponding operational event profiles from the basic scheduling information of the boiler to be scheduled. The basic scheduling information includes the turbine runner plan, the daily injection report, the boiler maintenance plan, and the set of abnormal events that have occurred in the boiler and their impacts. The operational event profiles include the events, future operation and maintenance requirements, and the health status of the boiler. The scheduling unit extracts necessary scheduling information from the operational event profile of the boiler to be scheduled and inputs it into the static collaborative optimization model to obtain the weekly schedule of the boiler to be scheduled. The necessary scheduling information extracted includes abnormal events, operational behaviors, and abnormal risk results. The static collaborative optimization model uses an optimization algorithm to solve the objective function while meeting the constraints required for scheduling to obtain the weekly schedule.

8. The steam injection boiler collaborative scheduling device based on multi-event states according to claim 7, characterized in that, It also includes an evaluation unit that simulates the weekly schedule of the boiler to be scheduled, and readjusts the weekly schedule if the simulation results are unsatisfactory, including: For the weekly scheduling of boilers to be scheduled, obtain the remaining duration and risk level of each event in the weekly scheduling; Based on the weekly schedule, the remaining duration and risk level of each event in the weekly schedule, the Monte Carlo simulation method is used to randomly simulate the scenarios of each event occurring in the boiler to be scheduled, and the boiler gas supply performance is obtained through simulation. Analyze the gas supply performance of the boiler to determine whether the gas supply performance is up to standard. In response to unsatisfactory boiler gas supply performance, the weekly schedule of the boilers to be scheduled will be readjusted. The readjustment methods include manual modification and adjustment of the parameters of the static collaborative optimization model.

9. A storage medium, characterized in that, The storage medium stores a computer program that can be read by a computer, and the computer program is configured to execute the multi-event state-based collaborative scheduling method for steam injection boilers as described in any one of claims 1 to 6 when it runs.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, which is loaded and executed by the processor to implement the multi-event state-based collaborative scheduling method for steam injection boilers as described in any one of claims 1 to 6.

Images