Process factory digital twinning implementation method and system based on dynamic number quality analysis

Abstract

The invention provides a process factory digital twinning implementation method and system based on dynamic number quality analysis, and relates to the technical field of process factory digital management.The process factory digital twinning implementation method comprises the steps that firstly, process link characteristic data and initial material input data of a process factory are obtained, and a process flow model reflecting the relation between process link connection and material transfer is constructed; performing analog calculation based on the technological process model and the initial data to obtain theoretical number quality data, and introducing a material attribute transmission attenuation coefficient; acquiring real-time number quality data of key process links, performing multi-device data fusion processing, and performing comparative analysis on the data and theoretical data to obtain a number quality deviation analysis result containing deviation propagation path information; and a process parameter adjustment instruction containing adjustment effect prediction information is generated according to the number quality deviation analysis result and sent to the control terminal, and dynamic monitoring, accurate analysis and intelligent regulation and control of the process factory are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital management of process plants, and in particular to a method and system for implementing digital twins of process plants based on dynamic data quality analysis. Background Art

[0002] Achieving efficient, stable, and high-quality production is a core goal in process plant operations. Traditional process plant management and control methods rely primarily on manual experience and regular testing and analysis. Understanding and optimizing process flows often relies on experienced engineers' intuitive understanding of process steps, lacking systematic and precise models to describe the complex relationships between these steps and the dynamics of materials within them. This makes it difficult to quickly and accurately make adjustments in the face of dynamic changes in the production process. Furthermore, traditional data collection and analysis methods typically rely on a single device, resulting in limited data volumes and susceptible to equipment inaccuracies and malfunctions. Furthermore, the lack of effective data fusion mechanisms prevents the collected data from fully and accurately reflecting actual production conditions. Furthermore, simple comparative analysis of collected data fails to delve into the underlying deviation paths, making it difficult to fundamentally identify the key factors affecting production quality. Consequently, precise process parameter adjustments are impossible, limiting improvements in process plant production efficiency and product quality. Summary of the Invention

[0003] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a method for implementing a digital twin of a process plant based on dynamic data quality analysis, the method comprising: Obtaining process link characteristic data and initial material input data of the process plant, wherein the process link characteristic data includes regular information on how each process link implements material processing functions, and the initial material input data includes basic attribute information of the materials; A process flow model is constructed based on the process link characteristic data and the initial material input data. The process flow model is used to reflect the connection relationship between each process link and the material transfer relationship between each process link. The process flow model can receive the material input data and output the material processing result data of the corresponding process link; Performing a process simulation calculation based on the process flow model and the initial material input data to obtain theoretical quantity and quality data for each process link, wherein the theoretical quantity and quality data include quantity information and quality information of the output material of each process link, and introducing a material property transfer attenuation coefficient into the process of the process flow simulation calculation; Collecting real-time data on quality and quality of each key process link in the process plant, processing the real-time data using a multi-device data fusion mechanism, and comparing and analyzing the processed real-time data with the theoretical data and quality of the corresponding process link to obtain a data and quality deviation analysis result, which includes information on the deviation propagation path; A process parameter adjustment instruction is generated based on the data and mass deviation analysis result, and the process parameter adjustment instruction is sent to the control terminal of the process plant to adjust the operating parameters of the corresponding process link. The process parameter adjustment instruction includes adjustment effect prediction information.

[0004] On the other hand, an embodiment of the present invention also provides a process plant digital twin implementation system based on dynamic data quality analysis, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0005] Based on the above aspects, the embodiment of the present invention constructs a process flow model by acquiring process link characteristic data and initial material input data, which can reflect the connection and material transfer relationship of each process link, and performs process flow simulation calculation based on the process flow model and introduces the material property transfer attenuation coefficient to obtain the theoretical numerical and quality data of each process link, so that the simulation results are closer to the actual production situation. The real-time numerical and quality data of the key process links are collected and processed using a multi-device data fusion mechanism. The processed real-time data is compared and analyzed with the theoretical data to obtain the numerical and quality deviation analysis results containing the deviation propagation path information, which can deeply explore the root causes of problems in the production process, generate process parameter adjustment instructions containing adjustment effect prediction information based on the analysis results and send them to the control terminal, realizing the precise adjustment of the process link operating parameters, realizing dynamic monitoring, precise analysis and intelligent control of the process factory production process, and effectively improving production efficiency, product quality and production stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 It is a schematic diagram of the execution flow of the process factory digital twin implementation method based on dynamic data quality analysis provided in an embodiment of the present invention.

[0007] Figure 2 This is a schematic diagram of exemplary hardware and software components of a process plant digital twin implementation system based on dynamic data quality analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0008] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1This is a flow chart of a method for implementing a digital twin of a process plant based on dynamic data quality analysis provided by an embodiment of the present invention. The following is a detailed introduction to the method for implementing a digital twin of a process plant based on dynamic data quality analysis.

[0009] Step S110: Acquire process link characteristic data and initial material input data of the process plant, wherein the process link characteristic data includes regular information of each process link in realizing material processing functions, and the initial material input data includes basic attribute information of the material.

[0010] In a coal washing plant, process characteristic data must be collected across all key equipment involved in material handling. For the raw coal crushing process, data on particle size distribution patterns under different crushing tooth shapes and rotational speeds must be collected, including data related to the proportion of each size range in the crushed material, crushing time, and feed rate.

[0011] For the heavy medium sorting process, it is necessary to obtain the corresponding relationship between the sorting density, medium circulation volume and the yield and ash content of clean coal, medium coal, gangue, etc., covering the change law of sorting efficiency under different raw coal properties, as well as data on the impact of the medium magnetic content on the sorting effect.

[0012] The characteristic data of the flotation process include the type and dosage of flotation agents, pulp concentration, the relationship between aeration volume and flotation clean coal yield and ash content, as well as the influence of scraping speed on flotation effect. The above data are compiled by simulating process operation under different working conditions in the laboratory and combining with long-term on-site production records to form a structured process link characteristic data set.

[0013] Initial material input data, based on raw coal, includes industrial analytical data such as ash content, volatile matter, and fixed carbon content, as well as elemental analysis data for carbon, hydrogen, oxygen, nitrogen, and sulfur content. It also includes physical properties such as true density, apparent density, hardness, grindability index, and particle size composition—the mass percentage of each size class. These data are determined using standard coal testing methods after raw coal sampling. For example, ash content is determined by slow ashing, volatile matter is determined by heating in a muffle furnace insulated from air, and particle size composition is determined by sieving analysis, forming a complete initial material input data archive.

[0014] Step S120: Construct a process flow model based on the process link characteristic data and the initial material input data. The process flow model is used to reflect the connection relationship between each process link and the material transfer relationship between each process link. The process flow model can receive material input data and output material processing result data of the corresponding process link.

[0015] Step S121: classify and organize the characteristic data of the process links, and extract the material processing rule information of each process link. The material processing rule information includes the change rules of the input material after being processed by the process link and converted into the output material.

[0016] Step S1211: Classify the process link characteristic data according to the function type of the process link, and the function type includes a material mixing function type, a material separation function type, and a material transportation function type.

[0017] In a coal washing plant, when process characteristic data is categorized by functional type, the material mixing functional type includes process steps such as flotation machines and mixing drums. Flotation machines use impellers to thoroughly mix slurry, reagents, and air. Its characteristic data includes the relationship between stirring intensity, stirring time, and mixing uniformity. The mixing drum is used to pre-mix reagents with slurry, and its characteristic data includes information related to stirring speed and reagent dispersion effectiveness.

[0018] Material separation functions include dense medium separators, jigs, screening equipment, and filters. Dense medium separators use density differences to separate materials of different compositions, and their characteristic data includes the relationship between separation density and separation efficiency. Jigs use water pulsation to separate materials by density, and their characteristic data includes the relationship between pulsation frequency and amplitude and separation effect. Screening equipment separates materials based on particle size differences, and its characteristic data covers the relationship between screen aperture, vibration frequency, and screening efficiency. Filters use filter media to achieve solid-liquid separation, and their characteristic data includes the relationship between filtration pressure, filter cloth type, and filter cake moisture content.

[0019] Material transport function types include process links such as belt conveyors, scraper conveyors, and bucket elevators. Belt conveyor characteristic data includes the relationship between belt speed and belt width and conveying capacity; scraper conveyor characteristic data relates to the relationship between scraper chain speed and conveying capacity; and bucket elevator characteristic data includes the correspondence between lifting speed and lifting capacity. This classification method provides a clearer structure for process link characteristic data, facilitating subsequent extraction of information on material handling patterns.

[0020] Step S1212: For the process link characteristic data under each functional type, extract the information describing the correspondence between the material input attributes, processing parameters and output attributes. The input attributes include the composition and status information of the material, the processing parameters include the operating parameters when the process link is running, and the output attributes include the composition and status information of the processed material.

[0021] For flotation machines with material mixing functions, the corresponding relationships between input attributes, process parameters, and output attributes are extracted from their characteristic data. Input attributes include the solids content in the slurry, the proportion of each mineral component, and the slurry temperature; process parameters include the flotation machine impeller speed, reagent addition amount, and aeration volume; and output attributes include the uniformity of the mixed slurry and the dispersion concentration of the reagent in the slurry.

[0022] For the heavy medium separator in the material separation function type, the input attributes are the ash content of the feed material, the content of materials at each density level, and the moisture content; the processing parameters include the sorting density, medium circulation volume, and drum speed; the output attributes are the ash content, yield, and moisture content of clean coal, medium coal, and gangue.

[0023] For belt conveyors in the material transportation function type, the input attributes are the particle size composition and bulk density of the conveyed material; the processing parameters include the conveyor belt speed and conveyor belt inclination; and the output attributes are the conveying volume per unit time and the uniformity of material distribution on the conveyor belt. By extracting these corresponding relationship information.

[0024] Step S1213: Optimize the correspondence information between the extracted input attributes, processing parameters and output attributes, remove duplicate and contradictory information, and form a preliminary material processing relationship data set.

[0025] When processing process characteristic data from a coal washing plant, the extracted correspondence information needs to be optimized. For duplicate information, such as in flotation machine characteristic data where the same set of input attributes and processing parameters correspond to multiple sets of identical output attribute records, only one record is retained to reduce data redundancy.

[0026] Contradictory information, such as in the characteristic data of a dense medium separator, where the same input attributes and processing parameters correspond to two sets of significantly different output attributes, requires verification. Verify the data's accuracy by reviewing the original experimental records or production logs. If the discrepancy is due to a recording error, correct the data. If the discrepancy is due to fluctuations in actual operating conditions, retain both sets of data and note the cause of the fluctuation.

[0027] In the case of missing data, if the amount of missing data is small, reasonable interpolation can be performed based on the changing trends of adjacent data. If the amount of missing data is large, it is necessary to mark this part of the data as missing and take it into account in subsequent analysis. After the above optimization process, a preliminary material processing relationship data set is formed to ensure data accuracy and consistency.

[0028] Step S1214: Based on the preliminary material processing relationship data set, through data fitting and rule induction, construct the change rules for converting the input materials into output materials after being processed through the process links. The change rules are used to clarify the output attributes corresponding to the combination of input attributes and processing process parameters.

[0029] Based on a preliminary data set of material processing relationships, using the heavy medium separation process as an example, a data fitting method was used to process the data between input attributes (such as feed ash content and particle size composition), process parameters (such as separation density and medium circulation rate), and output attributes (such as clean coal yield and ash content). By plotting data distribution trends and selecting the appropriate fitting curve type, a mathematical relationship between input and output was established.

[0030] At the same time, rules were summarized and analyzed to show how clean coal yield and ash content change when the sorting density changes within a certain range. For example, when the sorting density increases and other parameters remain unchanged, the clean coal yield shows an upward trend, and the clean coal ash content also increases accordingly. When the medium circulation volume increases to a certain level, the improvement in sorting efficiency tends to be flat.

[0031] The above rules are fixed in the form of text description to form change rules, which clearly define the specific changes in output attributes under specific combinations of input attributes and processing parameters, such as "when the feed ash content is within a certain range, the sorting density is set to a certain value, and the medium circulation volume is at a certain level, the clean coal yield is within a certain range and the ash content is within a certain range."

[0032] Step S1215: setting a dynamic correction factor for the change rule, wherein the dynamic correction factor can be adjusted according to the operation time of the process link and the maintenance record.

[0033] Set a dynamic correction factor for the changing rules of the heavy medium separation process. This dynamic correction factor is initially set to a baseline value and increases gradually as the heavy medium separator's operating time increases. For example, with each increase in operating time, the correction factor increases proportionally from the baseline value to reflect the decrease in separation efficiency caused by equipment wear. For example, if the drum liner wears, the deviation between the actual separation density and the set value increases. The dynamic correction factor adjusts the calculated output attribute.

[0034] When a heavy medium separator undergoes maintenance, such as replacing drum liners or adjusting transmissions, the dynamic correction factor is reset to the baseline value based on the maintenance records to reflect the recovery of equipment performance. For flotation machines, the dynamic correction factor is adjusted based on the operating time of the impeller. As the impeller wears, the agitation intensity decreases, and the correction factor is adjusted accordingly to correct the calculated mixing effect. After the impeller is replaced, the correction factor returns to its initial value.

[0035] Step S1216: Associating the change rule with the identification information of the corresponding process link to form the material processing rule information of each process link, and at the same time performing format standardization processing on the material processing rule information.

[0036] Associate the change rules for the heavy medium separation process with its identification information, including the equipment number, equipment name, and workshop location. For example, associate the "change rule for heavy medium separator M-01" with the equipment number "M-01," name "heavy medium roller separator," and location "Separation Workshop Area A" to ensure that each change rule accurately maps to a specific process step.

[0037] The format of material processing rule information is standardized, using a unified structured data format. For example, each rule information is required to include input attribute fields, processing process parameter fields, output attribute fields, dynamic correction factor fields, process link identification fields, etc. The naming method of each field is unified, and the data type is clear. For example, the ash content in the input attribute field is expressed as a percentage, the sorting density in the processing process parameter field is expressed in grams per cubic centimeter, and the yield in the output attribute field is expressed as a percentage. This ensures that the format of material processing rule information in different process links is consistent, facilitating the unified call and processing of the process flow model.

[0038] Step S122: According to the actual production process of the process plant, the material transfer sequence between each process link is determined to form a process link transfer relationship list, in which the corresponding relationship between the input port and the output port of the adjacent process links is recorded.

[0039] In a coal washing plant, the material transfer sequence for each process step is organized according to the actual production process. Raw coal first enters the raw coal silo and is transported by a coal feeder to the crushing stage. The crushed material is then transported by a belt conveyor to the screening stage. The oversize material from the screening stage is returned to the crushing stage via another belt conveyor, while the undersize material is transported by a belt conveyor to the dense medium separation stage.

[0040] The clean coal from the heavy medium separation stage is transported to the dewatering stage via a scraper conveyor. The middlings and gangue are then transported to their respective subsequent processing stages via separate belt conveyors. The clean coal from the dewatering stage is then transported to the clean coal silo via a belt conveyor. The filtrate from the dewatering stage is then piped to a circulating water tank.

[0041] Following the above transfer sequence, a list of process link transfer relationships is generated. This list details the correspondence between the input and output ports of adjacent process links. For example, the output port "crushed material outlet" of the crushing link corresponds to the input port "screening inlet" of the screening link; the output port "oversize outlet" of the screening link corresponds to the input port "return material inlet" of the crushing link; the output port "undersize outlet" of the screening link corresponds to the input port "separation inlet" of the heavy medium separation link, and so on. Each port is labeled with its type, such as solid material outlet, liquid material outlet, solid material inlet, etc., to ensure the accuracy of material transfer relationships.

[0042] Step S123: Call the process flow modeling tool, drag and drop the graphic symbols corresponding to each process link according to the process link transfer relationship list, establish connecting lines between the graphic symbols of each process link to represent the material transfer path, and preliminarily build the process flow model framework.

[0043] Call a special process flow modeling tool. The graphic library of this process flow modeling tool contains graphic symbols corresponding to each process link, such as the crushing link corresponds to the crusher model graphic symbol, the screening link corresponds to the screening model graphic symbol, the heavy medium separation link corresponds to the separation model graphic symbol, etc.

[0044] Based on the process link transfer relationship list, drag and drop the graphic symbols of each process link on the modeling tool canvas, and arrange them according to the spatial layout and process sequence in actual production. For example, place the graphic symbol of the raw coal bunker on the left, and the graphic symbols of the coal feeder and crushing link to its right. Place the graphic symbol of the screening link to the right of the crushing link, and place the graphic symbol of the heavy medium separation link to the right of the screening link, and so on.

[0045] Next, use the line drawing function within the modeling tool to create connecting lines between the graphical symbols of adjacent process links. The starting point of the connecting line is the graphical symbol position corresponding to the output port of the previous process link, and the end point is the graphical symbol position corresponding to the input port of the next process link. For example, draw a line from the "crushing material outlet" position of the crushing process graphical symbol to the "screening inlet" position of the screening process graphical symbol to represent the path of material transfer from the crushing stage to the screening stage. Through these operations, a preliminary process flow model framework is constructed, which intuitively displays the connection relationship between each process link and the material transfer path.

[0046] Step S124: Encapsulate the material handling rule information of each process link into the corresponding process link graphic symbol, set a parameter configuration interface for the process flow model framework, and the parameter configuration interface can receive external input process parameter adjustment data.

[0047] In the process modeling tool, select the graphic symbol for each process step and, using the tool's property configuration function, encapsulate the previously organized material handling information for each process step within the graphic symbol. During the encapsulation process, a mapping relationship is established between the graphic symbol and the material handling information, so that when the graphic symbol is triggered, the corresponding handling information can be called up for calculation.

[0048] Set up a parameter configuration interface for the process model framework. This interface includes multiple parameter input items corresponding to the processing parameters of each process step. For example, set up input items for parameters such as separation density and medium circulation rate for the graphic symbol of the heavy medium separation step, and set up input items for parameters such as reagent dosage and slurry concentration for the graphic symbol of the flotation step.

[0049] The parameter configuration interface supports the input of external data. Operators or other systems can use this interface to input process parameter adjustment data, such as adjusting the sorting density value of the heavy medium separation link. The adjusted parameters will be passed to the corresponding process link graphic symbol to update the processing process parameters in the material processing law information, thereby affecting the calculation results of the model.

[0050] Step S125: establishing a dynamic update interface for process link characteristics, wherein the dynamic update interface for process link characteristics can receive real-time collected process link operation status data, and update the material handling rule information of the corresponding process link according to the process link operation status data.

[0051] The dynamic update interface for process characteristics is connected to the factory's real-time data acquisition system, which can receive real-time data on the operating status of each process link. This data includes equipment operating current, voltage, temperature, vibration frequency, motor speed, etc.

[0052] For example, real-time operating status data for a dense medium separator includes the actual drum speed, bearing temperature, and motor current; real-time operating status data for a flotation machine includes impeller speed, aeration volume, and slurry level. Once this operating status data is transmitted to the dynamic update interface, the interface determines its impact on material processing information based on pre-set association rules.

[0053] If there is a deviation between the actual speed of the drum of the heavy medium separator and the set speed, the dynamic update interface will adjust the correction coefficient corresponding to the speed parameter in the material processing rule information of the process link according to the deviation value, and then update the output attribute calculation logic related to the speed in the change rule; if the bearing temperature of the flotation machine exceeds the normal range, the interface will trigger the adjustment of the dynamic correction factor in the material processing rule information to reflect the impact of equipment overheating on the mixing effect, ensuring that the material processing rule information can reflect the actual operating status of the process link in real time.

[0054] Step S126: input the initial material input data into the parameter configuration interface, trigger the process flow model framework to perform material processing simulation according to the material processing rule information of each process link, generate simulation output data of each process link, and complete the construction of the process flow model.

[0055] Initial material input data, such as the ash content, particle size composition, and moisture content of the raw coal, is entered into the process model framework through the parameter configuration interface. The parameter configuration interface performs format verification on the input initial material input data to ensure that the data format is consistent with the model requirements. For example, ash content is entered as a percentage, and particle size composition is entered as the mass percentage of each particle size range. If the data format does not meet the requirements, the interface will return an error message, and the data must be adjusted and re-entered.

[0056] After the initial material input data passes verification, the process flow model framework is triggered to start running. The model framework follows the order of the process link transfer relationship list, starting with the process link corresponding to the raw coal bunker, and sequentially calls the material handling rule information encapsulated in the graphic symbols of each process link.

[0057] Taking the raw coal entering the crushing stage as an example, the model uses the raw coal particle size composition, moisture content and other data in the initial material input data as the input attributes of the crushing stage, combines the processing parameters of the crushing stage (such as crusher speed, parameters corresponding to the crushing tooth shape, etc.), and calculates according to the material processing rules of the crushing stage to obtain simulated output data such as the particle size composition and output of the crushed material.

[0058] The simulated output data from the crushing stage is transmitted as input to the screening stage via the material transfer path in the model. The screening stage uses its own material processing information and combines it with the screening equipment's process parameters, such as mesh aperture and vibration frequency, to simulate the crushed material input, generating simulated output data such as the particle size composition and yield of the oversize and undersize materials. The simulated output data for the oversize material is returned to the crushing stage via the corresponding transfer path, while the simulated output data for the undersize material is transmitted to the dense medium separation stage.

[0059] After receiving the simulated output data of the undersize material, the heavy medium separation link uses this data as input attributes, combines it with processing parameters such as separation density and medium circulation volume, and performs simulation calculations based on its own material processing law information to obtain simulated output data such as the yield, ash content, and moisture content of clean coal, medium coal, and gangue. The above data are transmitted to the subsequent dehydration link and the medium coal and gangue processing links through corresponding transmission paths.

[0060] Each subsequent process link performs material handling simulation in sequence according to the above method until the simulation output data such as the clean coal quality and ash content in the clean coal bin and the filtrate volume in the circulating water pool are finally generated.

[0061] Throughout the simulation process, the model framework records the simulation output data of each process step in real time, including information such as the data generation time and the corresponding process step identifier. After the simulation output data of all process steps is generated, it is aggregated and organized to form a complete simulation result data set.

[0062] Step S130: Perform process flow simulation calculation based on the process flow model and the initial material input data to obtain theoretical quantity and quality data of each process link. The theoretical quantity and quality data include quantity information and quality information of the output materials of each process link. The material property transfer attenuation coefficient is introduced in the process of process flow simulation calculation.

[0063] Launch the completed process model and re-enter the initial material input data into the model's parameter configuration interface. The model then begins simulating the process according to the pre-set calculation logic. During the calculation, a material property transfer attenuation coefficient is introduced to account for changes in quantity and quality attributes caused by factors such as equipment loss and residual material during material transfer.

[0064] The simulation begins with the initial process step and progresses backward. After each step is calculated, the corresponding theoretical data is output, including the quantity (e.g., yield, volume) and quality (e.g., ash content, moisture content, purity, etc.) of the output material at that step. After all process steps are calculated, the theoretical data for each step is summarized to form a complete theoretical data set.

[0065] Step S131: inputting the initial material input data into the process flow model through the parameter configuration interface of the process flow model, and determining the starting process link corresponding to the initial material input data.

[0066] The initial material input data is organized into a structured data format that the model can recognize and input into the model through the process model's parameter configuration interface. The parameter configuration interface parses the input data and extracts material source information, such as the initial feed point of the raw coal.

[0067] Based on the material source information, the corresponding process link is searched in the process flow model. In the coal washing process, the starting process link corresponding to the initial material input data is usually the raw coal bunker. The model matches the process link identification information and determines that the process link corresponding to the raw coal bunker is the starting process link for this simulation calculation.

[0068] Step S132: Using the process flow model, starting from the starting process link in the order of the process link transfer relationship list, calling the material processing rule information encapsulated in the process link to process the input initial material input data, and generating the intermediate material output data of the starting process link.

[0069] The process flow model reads the process link transfer relationship list, clarifies that the first process link after the starting process link (raw coal bin) is the coal feeder, and the material transfer path between the two.

[0070] The model begins with the initial process (the raw coal bunker) and calls upon the material handling rules encapsulated within that process. This information includes the relationship between the raw coal storage capacity and the discharge rate, as well as the particle size changes during discharge.

[0071] The data related to the raw coal bin (such as raw coal storage capacity, initial particle size, etc.) in the input initial material input data is used as input attributes and substituted into the material processing law information of the raw coal bin. Combined with the processing process parameters such as the feed speed of the coal feeder, calculation is performed to obtain the intermediate material output data such as the material quantity and particle size output from the raw coal bin to the coal feeder.

[0072] The intermediate material output data is marked with the starting process link identifier (raw coal bunker number) and processing timestamp, and stored in the temporary data storage area of ​​the model.

[0073] Step S1321: The process flow model reads the process link transfer relationship list to determine the identifier of the starting process link and the storage path of the material processing rule information corresponding to the starting process link.

[0074] The process flow model opens the process link transfer relationship list and extracts the identification information of the starting process link, such as "Raw Coal Bin-Y01." Based on this identification information, the model searches the preset storage directory for the corresponding material handling rule information storage path. This path is typically stored in a folder named after the process link, such as " / process_data / Raw Coal Bin-Y01 / handling_rules / ."

[0075] The model verifies the validity of the storage path, ensuring that it exists and contains complete material handling rule information files, such as rule description files and parameter configuration files. If the path is invalid, the model returns an error message, prompting you to check the process link transfer relationship list and the storage status of the material handling rule information.

[0076] Step S1322: calling the material processing rule information encapsulated in the initial process link through the storage path, and loading the material processing change rules and dynamic correction factors therein.

[0077] Based on the determined storage path, the model accesses the corresponding folder and reads the material handling rule information file. It then parses the rule description file and extracts the material handling variation rules, such as the relationship between the discharge volume and storage volume of the raw coal bunker, the opening degree of the discharge valve, and the variation of raw coal particle size under different storage volumes.

[0078] At the same time, the dynamic correction factor in the parameter configuration file is read. The dynamic correction factor is used to reflect the impact of the aging degree of the raw coal bunker equipment on the discharge accuracy. For example, as the sealing performance of the discharge port valve decreases with the increase in usage time, the correction value corresponding to the change in material residual amount

[0079] The model stores the loaded material handling change rules and dynamic correction factors in memory so that they can be quickly called up in subsequent calculation processes.

[0080] Step S1323: convert the input initial material input data into the format required by the material processing rule information, extract the input attribute information in the initial material input data, and match it with the input attribute items in the material processing change rule.

[0081] Initial material input data may contain data in various formats, such as text-based test reports and tabular analysis data. Based on the input data format requirements in the material processing law information, the model converts the initial material input data into a unified structured data format, such as JSON or XML.

[0082] After the conversion is completed, input attribute information is extracted from the structured data, such as the storage capacity, average particle size, moisture content, etc. of the raw coal. The above input attribute information is matched one by one with the input attribute items in the material processing change rules to check whether there are any missing attribute items.

[0083] If there are any unmatched input attributes, the model will check whether the attribute is optional. If it is optional, the model will use the default value to fill it in. If it is required, the model will prompt that the corresponding input attribute information is missing and needs to be completed before reprocessing.

[0084] Step S1324: Based on the matched input attribute information and the material processing change rules, the default values ​​of the processing parameters under the current operating state of the starting process link are determined. If the initial material input data contains processing parameter adjustment information, the default values ​​of the processing parameters are replaced with the parameter values ​​in the adjustment information.

[0085] Based on the matched input attribute information (such as the raw coal storage volume is within a certain range), the model searches for the corresponding default values ​​of the processing parameters in the material processing change rules, such as the initial opening of the raw coal bin discharge valve and the initial feeding speed of the coal feeder.

[0086] Checks whether the initial material input data contains any process parameter adjustments, such as adjustments to the coal feeder feed rate by the operator based on the production plan. If so, the model replaces the default process parameter values ​​with the adjusted values ​​to ensure that the parameter settings meet actual production requirements.

[0087] After the replacement is completed, the model performs a rationality check on the processing parameters to ensure that the parameter values ​​are within the allowable range (such as the valve opening is between 0-100%). If the parameter value is out of range, the model will return a prompt message and continue processing after the parameters are adjusted correctly.

[0088] Step S1325: Based on the matched input attribute information, the determined processing parameter value and the dynamic correction factor, they are substituted into the material processing change rule for calculation to obtain the output attribute information of the material after processing in the initial process link.

[0089] The matched input attribute information (such as raw coal storage volume, average particle size, etc.), determined processing process parameter values ​​(such as valve opening, coal feeder feeding speed, etc.) and dynamic correction factors (such as correction values ​​reflecting equipment aging) are substituted into the calculation logic of the material processing change rules.

[0090] Taking the material output calculation of the raw coal bin as an example, the basic discharge volume is calculated based on the storage capacity and valve opening, and then the basic discharge volume is corrected by the dynamic correction factor to obtain the actual discharge volume; at the same time, according to the average particle size of the raw coal and the processing parameters, the particle size distribution change of the discharge is calculated to obtain the particle size properties of the processed material.

[0091] Through the above calculations, the output property information of the material after processing in the initial process link is obtained, including the output volume, particle size distribution, moisture content, etc.

[0092] Step S1326: Associating the material output attribute information with the starting process link identifier and processing time information to generate intermediate material output data of the starting process link, and storing the intermediate material output data in the temporary data storage module of the process flow model.

[0093] The material output attribute information after processing in the initial process link (such as the material quantity, particle size distribution, moisture content, etc. output from the raw coal bin) is associated with the identification information of the initial process link (such as "raw coal bin-Y01"), processing start time and end time and other processing time information to form a complete set of intermediate material output data.

[0094] Intermediate material output data is stored in a structured format, including fields such as "process step identification", "processing start time", "processing end time", "discharge volume", "particle size distribution", and "moisture content".

[0095] The generated intermediate material output data is transferred to the temporary data storage module of the process flow model. This temporary data storage module uses partitioned storage to categorize and store data according to process step identifiers, facilitating quick query and access in subsequent process steps. Furthermore, the temporary data storage module backs up the data to prevent data loss.

[0096] Step S133: Determine the material property transfer attenuation coefficient based on the material transfer distance and transfer method between process links. The material property transfer attenuation coefficient includes the material quantity transfer attenuation coefficient and the material quality property attenuation coefficient, which is used to correct the property loss of the material during the transfer process.

[0097] Measure the material transfer distance between adjacent process links. For example, the material transfer distance from the coal feeder to the crusher is obtained by measuring the length of the conveyor belt between the two, and the transfer distance from the crusher to the screening machine is obtained by measuring the length of the corresponding pipeline or conveyor belt.

[0098] Determine the material transfer method between each process link, such as using a belt conveyor to transfer from the coal feeder to the crusher, using a chute to transfer from the crusher to the screening machine, and using pipeline pumping to transfer from the heavy medium separator to the dehydrator.

[0099] Query the preset attenuation coefficient calculation rules based on the transfer distance and transfer method. For belt conveyor transfer, the longer the transfer distance, the more material spillage and residue during transportation, and the greater the material quantity transfer attenuation coefficient. For chute transfer, considering the friction loss of the material within the chute, the longer the transfer distance, the greater the quantity transfer attenuation coefficient.

[0100] Regarding the material quality attribute attenuation coefficient, if the delivery method is pipeline pumping and the material is slurry, long-term delivery may cause the solid particles in the slurry to settle, affecting the particle size distribution of the material. At this time, the quality attribute attenuation coefficient is determined based on the delivery time (calculated by the delivery distance and delivery speed); if there is a temperature change during the delivery process, it may affect the moisture content of the material. The quality attribute attenuation coefficient needs to be adjusted based on the temperature change amplitude.

[0101] Taking the above factors into consideration, the material quantity transfer attenuation coefficient and the material quality attribute attenuation coefficient between each process link are calculated to form an attenuation coefficient list for subsequent material transfer correction calculation.

[0102] Step S134: Use the material quantity transfer attenuation coefficient to perform attenuation correction on the quantity information in the intermediate material output data of the starting process link, and use the material quality attribute attenuation coefficient to perform attenuation correction on the quality information in the intermediate material output data of the starting process link to obtain the corrected intermediate material output data, use the corrected intermediate material output data as the input data of the next process link, call the material processing rule information encapsulated in the next process link for processing, and generate the intermediate material output data of the next process link.

[0103] Quantity information, such as discharge volume, is extracted from the intermediate material output data of the initial process link (raw coal bunker). This discharge volume is corrected based on the material quantity transfer attenuation coefficient between the raw coal bunker and the next process link (coal feeder). The corrected discharge volume is equal to the original discharge volume multiplied by (1 minus the quantity transfer attenuation coefficient) to reflect material quantity loss during the transfer process.

[0104] Extract quality information from the output data of intermediate materials in the initial process, such as moisture content and particle size distribution. Based on the corresponding material quality attribute attenuation coefficient, correct the moisture content (for example, to account for moisture loss caused by evaporation during transfer) and the particle size distribution (for example, to account for subtle changes in particle size caused by collisions during transfer) to obtain the corrected quality information.

[0105] The corrected quantity information and quality information are combined to form corrected intermediate material output data, which is used as input data of the coal feeder and transmitted to the corresponding process link of the coal feeder.

[0106] The coal feeder process link calls the material processing law information encapsulated by itself, combines the input corrected intermediate material output data and its own processing process parameters (such as coal feeding speed adjustment parameters) for processing, and generates the intermediate material output data of the coal feeder, including coal feeding amount, coal feeding uniformity and other information.

[0107] Step S135: Repeat the above steps of determining the material property transfer attenuation coefficient, performing attenuation correction on the intermediate material output data of the previous process link and processing it as input data for the next process link, until the material processing simulation of all process links is completed and the final material output data of the final process link is obtained.

[0108] Starting from the intermediate material output data of the coal feeder, determine the material transfer distance and transfer method (such as belt conveyor) between the coal feeder and the crusher, and query the corresponding material property transfer attenuation coefficient.

[0109] The quantity information (such as coal feeding amount) and quality information (such as coal particle size) in the intermediate material output data of the coal feeder are attenuated and corrected, and the corrected input data is transmitted to the crusher process link.

[0110] The crusher process calls on its own material processing law information, combines the corrected input data and the crusher's processing parameters (such as crushing speed, crushing gap, etc.) for processing, and generates the crusher's intermediate material output data (such as the particle size distribution and output of the coal after crushing).

[0111] According to the above process, the screening machine, heavy medium separator, dehydrator and other process links are processed in sequence. Each process link repeats the steps of determining the attenuation coefficient, correcting the previous data, and processing the current link.

[0112] Until the material has been processed through all process links, the final material output data is generated, including the clean coal quantity, ash content, moisture content in the clean coal bin, the material quantity and quality information in the medium coal bin and gangue bin, and the filtrate volume in the circulating water pool.

[0113] Step S136: sorting the intermediate material output data generated by each process link and the final material output data of the final process link, extracting the quantity information and quality information therein, and forming the theoretical quantity and quality data of each process link.

[0114] Collect the intermediate material output data and final material output data of all process links and sort them according to the sequence of the process links.

[0115] Extract quantity information from the output data of each process link, such as the discharge volume and conveying volume of each link; extract quality information, such as ash content, moisture content, particle size distribution, purity, etc.

[0116] The extracted quantity information and quality information are associated with the corresponding process link identification and data generation time to form a theoretical quantity and quality data record for each process link.

[0117] The theoretical numerical quality data of all process links are recorded and summarized to form a structured theoretical numerical quality data set, which can be stored in the form of a database table or Excel spreadsheet to facilitate subsequent query, comparative analysis and other operations.

[0118] Step S140: Collect real-time data on the quality of each key process link in the process plant, process the real-time data on the quality of each key process link using a multi-device data fusion mechanism, and compare and analyze the processed real-time data on the quality of each key process link to obtain a quality deviation analysis result, which includes information on the deviation propagation path.

[0119] Based on the process flow and product characteristics of the process plant, the heavy medium separator, dewatering machine, and flotation machine are identified as key process links. Data and quality collection equipment is installed at the output ports of these key process links. For example, a belt scale and an online ash analyzer are installed at the clean coal output port of the heavy medium separator, and a moisture meter and yield meter are installed at the discharge port of the dewatering machine.

[0120] The data and quality collection equipment collects real-time quantity data (such as output) and real-time quality data (such as ash content and moisture content) of key process links according to a preset collection cycle (such as once an hour).

[0121] The multiple sets of collected real-time data quality data are processed through a multi-device data fusion mechanism to eliminate outliers and redundant information in the data and obtain fused real-time data quality data.

[0122] The fused real-time quantitative and qualitative data are compared with the theoretical quantitative and qualitative data for the corresponding process steps, calculated from the process flow model, to calculate quantitative and qualitative deviations. Based on the connections between key process steps, the transmission paths of deviations between them are analyzed, ultimately generating quantitative and qualitative deviation analysis results that include information such as deviation values ​​and deviation propagation paths.

[0123] Step S141: According to the process flow and product composition of the process plant, determine the key process links that have a direct impact on the quantity and quality of the final product, and form a list of key process links.

[0124] Draw a complete process flow diagram for the process plant, labeling each process step, its input and output ports, and their interconnections. Analyze the composition of the final product (e.g., clean coal), clarifying that clean coal is formed by processing the clean coal product from the heavy medium separator through a dehydrator. Therefore, the heavy medium separator and dehydrator have a direct impact on the quantity and quality of the final clean coal.

[0125] At the same time, considering the recovery effect of the flotation link on fine-grained clean coal, the processing effect of the flotation machine will also affect the final output and quality of clean coal, so the flotation machine is also identified as a key process link.

[0126] Identify these key process links, record their equipment numbers, locations, main functions and other information, and form a list of key process links.

[0127] Step S1411: Based on the complete process flow of the process plant, a process flow diagram is drawn, and the input port, output port of each process link and the material transfer path between each process link are marked in the process flow diagram.

[0128] Collect process plant design data and equipment layout diagrams, and then outline all process steps from raw coal entry to final product output, including the raw coal bin, coal feeder, crusher, screen, dense medium separator, dewatering machine, flotation machine, filter, and product bin. Draw a process flow diagram based on the sequence and connection relationships of each process step.

[0129] In the block diagram, draw a corresponding graphic symbol for each process step, such as a rectangular box for the raw coal bin, a graphic with a pattern of crushing teeth for the crusher, and a graphic with a mesh pattern for the screening machine. Label each graphic symbol with its input and output ports, with arrows pointing from the graphic symbol to the input port and arrows leading from the graphic symbol to the output port. Next to the arrow is the material type, such as "raw coal," "crushed material," "undersize," or "clean coal."

[0130] Use solid lines to connect the output port of each process step with the input port of the next process step, forming a material transfer path. For example, a solid line connects the output port of the raw coal bunker to the input port of the coal feeder, which in turn connects to the input port of the crusher. The output port of the crusher connects to the input port of the screener, one output port of the screener connects to the input port of the dense medium separator, and another output port connects to the input port of the crusher (indicating that the oversize material is returned to the crusher). This approach clearly demonstrates the input-output relationship of each process step and the material transfer path in the process flow diagram.

[0131] Step S1412: Analyze the components of the final product and determine the material branches that constitute the final product. The material branch is the sequence of process links that the material goes through from the initial material input to the final product output.

[0132] The final product is clean coal. Analysis of its composition reveals that the clean coal is composed of coarse clean coal from the heavy medium separator and fine clean coal from the flotation machine. Based on this, the material branches that make up the final product are determined.

[0133] The first material branch is raw coal - raw coal bin - coal feeder - crusher - screening machine - heavy medium separator - dehydrator - clean coal bin. This branch corresponds to the production path of coarse-grained clean coal, covering all the process links from raw coal input to coarse-grained clean coal entering the clean coal bin.

[0134] The second material branch is raw coal – raw coal silo – coal feeder – crusher – screening machine – flotation machine – filter – clean coal silo. This branch corresponds to the production path of fine clean coal, encompassing every process step from raw coal input to the delivery of fine clean coal to the clean coal silo. By identifying these material branches, the critical paths that influence the final product are clearly defined.

[0135] Step S1413: For each material branch, from the initial process link to the final process link, analyze in turn the degree of influence of the output material of each process link on the material processing results of the subsequent process link, and use the influence factor evaluation method to calculate the influence factor value of each process link. The influence factor value represents the degree of influence of the process link on the subsequent material processing results.

[0136] Taking the first material branch (raw coal - raw coal silo - coal feeder - crusher - screening machine - dense medium separator - dewatering machine - clean coal silo) as an example, we analyze the process from the initial process step. The raw coal silo outputs raw coal, and its quality and quantity directly affect the feeder's conveying efficiency. If the raw coal particle size in the raw coal silo is uneven, it can cause fluctuations in the feeder's conveying capacity, which in turn affects the subsequent crushing step and has a certain impact on the subsequent processing results of this branch. The impact factor value is calculated using the impact factor evaluation method.

[0137] The stability of the output material flow of the coal feeder affects the load of the crusher. If the coal feeding amount is unstable, it may cause fluctuations in the crusher processing effect and affect the subsequent screening process. The impact factor value is calculated, which is slightly higher than the impact factor value of the raw coal bin.

[0138] The particle size of the crusher's output material directly determines the screening efficiency of the screening machine. If the particle size of the crushed material does not meet the requirements, it may cause the particle size of the screening material to exceed the standard, affecting the heavy medium separation effect. Its impact factor value is higher than that of the coal feeder.

[0139] The quality and quantity of the screening material directly enter the heavy medium separator. If the screening material contains too many large particles, it can increase the burden of the heavy medium separator and affect the sorting accuracy. Its impact factor value is higher than that of the crusher.

[0140] The quality and quantity of the clean coal products from the heavy medium separator are the input basis for the subsequent dehydration process. The sorting effect directly determines the quality of the final coarse-grained clean coal, and its influencing factor value is relatively high in this branch.

[0141] The treatment effect of the dehydrator affects the moisture content of the clean coal. If the dehydration is insufficient, the moisture content of the clean coal may exceed the standard, affecting the quality of the final product. Its impact factor value is lower than that of the heavy medium separator, but higher than some of the previous links.

[0142] The same method was used for the second material branch (raw coal - raw coal bin - coal feeder - crusher - screening machine - flotation machine - filter - clean coal bin) to analyze the influencing factor values ​​of each process link in turn. Among them, the influencing factor value of the flotation machine was higher in this branch because it directly determines the recovery rate and quality of fine-grained clean coal.

[0143] Step S1414: Screen out the process links in each material branch whose impact factor value is greater than the impact factor threshold as candidate key process links of the material branch.

[0144] The impact factor threshold is determined based on the production experience and process requirements of the process plant and is used to distinguish process links that have a greater impact on subsequent material processing results.

[0145] For the first material branch, the impact factor value of each process link is compared with the impact factor threshold. The impact factor values ​​of the heavy medium separator and the dehydrator are greater than the threshold, and they are screened as candidate key process links for this branch.

[0146] In the second material branch, through comparison, the impact factor values ​​of the flotation machine and the filter are greater than the threshold, and they become candidate key process links of this branch. The above candidate key process links are the links in each material branch that have a more significant impact on the quantity and quality of the final product.

[0147] Step S1415: Summarize the candidate key process links of all material branches, remove duplicate process links, mark each candidate key process link with its material branch and influencing factor value, and form a key process link list.

[0148] The candidate key process links of the first material branch (heavy medium separator, dehydrator) and the candidate key process links of the second material branch (flotation machine, filter) were summarized to check whether there were repeated process links. After inspection, no duplication was found.

[0149] Label each candidate key process link with its corresponding material branch and impact factor value. For example, label the heavy medium separator as "Branch: Coarse Clean Coal Production Path, Impact Factor: XX"; the dehydrator as "Branch: Coarse Clean Coal Production Path, Impact Factor: XX"; the flotation cell as "Branch: Fine Clean Coal Production Path, Impact Factor: XX"; and the filter as "Branch: Fine Clean Coal Production Path, Impact Factor: XX." Organize this information into a table to create a list of key process links.

[0150] Step S1416: Introduce the historical data of process link failures, and prioritize the candidate key process links in the key process link list. The candidate key process links with higher failure frequencies are ranked higher, and the key process link list is updated.

[0151] Collect historical failure data for each candidate key process link, including the number of failures of heavy medium separators, dehydrators, flotation machines, and filters over the past period of time, the duration of failures, and fluctuations in product quality caused by failures.

[0152] Statistics on the failure frequency of each candidate key process link show that the heavy medium separator has a higher failure frequency due to its complex structure and harsh operating conditions; the flotation machine has the second highest failure frequency because it involves reagent addition and slurry state control; the dewatering machine and filter have a relatively low failure frequency.

[0153] Prioritize candidate key process links based on failure frequency: dense medium separators ranked first, flotation cells second, dewatering machines third, and filters fourth. Update the key process link list based on this ranking to reflect the failure risk level of each key process link, facilitating subsequent focused monitoring.

[0154] Step S142: For each key process link in the key process link list, select at least two suitable data and quality acquisition devices, and the data and quality acquisition devices are used to collect real-time quantity information and real-time quality information of the output materials of the corresponding key process link.

[0155] For the heavy medium separator in the key process link list, select appropriate data and quality collection equipment. For quantity collection, electromagnetic flowmeters and vortex flowmeters are used. Both are suitable for the pipeline transportation environment of the heavy medium separator output material and can collect the material volume flow rate to reflect quantity information. For quality collection, online ash analyzers and X-ray fluorescence analyzers are used. The online ash analyzer can detect the ash content of clean coal in real time, and the X-ray fluorescence analyzer can analyze the elemental composition of the clean coal, indirectly reflecting quality information.

[0156] For flotation machines, turbine flowmeters and ultrasonic flowmeters are used as quantity collection equipment, which are suitable for measuring the flow rate of the flotation machine output slurry; near-infrared spectrometers and laser particle size analyzers are used as quality collection equipment. The near-infrared spectrometer can detect the composition of the flotation clean coal, and the laser particle size analyzer can analyze the particle size distribution of the clean coal as the basis for quality assessment.

[0157] For the dehydrator, the quantity collection equipment uses scraper flowmeters and rotor flowmeters to measure the delivery volume of clean coal after dehydration; the quality collection equipment uses microwave moisture meters and image analyzers. The microwave moisture meter can detect the moisture content of clean coal in real time, and the image analyzer evaluates the physical state of the clean coal by photographing its appearance.

[0158] The filter utilizes electromagnetic flowmeters and oval gear flowmeters for quantitative data collection, while infrared moisture meters and online viscometers for quality data collection. Each key process step is equipped with at least two units of quantitative and quality data collection equipment to enhance the reliability and accuracy of data collection.

[0159] Step S143: Start the data and quality collection device to collect real-time quantity information and real-time quality information of the output materials of each key process link according to a preset collection frequency, and obtain multiple groups of real-time data of data and quality of each key process link.

[0160] Start the electromagnetic flowmeter, vortex flowmeter, online ash analyzer and X-ray fluorescence analyzer equipped for the heavy medium separator, and at the same time start the turbine flowmeter, ultrasonic flowmeter, near-infrared spectrometer and laser particle size analyzer equipped for the flotation machine, as well as various data and mass collection equipment equipped for the dehydrator and filter.

[0161] The preset collection frequency is determined based on the dynamic characteristics of the process and production monitoring requirements to ensure timely capture of changes in material quantity and quality. Each data collection device collects real-time quantity and quality information of the output materials of the corresponding key process links at this frequency.

[0162] The electromagnetic flowmeter and vortex flowmeter of the heavy medium separator continuously collect the volume flow data of its output material according to the collection frequency, forming multiple sets of real-time quantity data; the online ash analyzer and X-ray fluorescence analyzer synchronously collect the ash content and elemental composition data of the clean coal, forming multiple sets of real-time quality data.

[0163] The turbine flowmeter and ultrasonic flowmeter of the flotation machine collect and output the flow data of the slurry according to the frequency, generating multiple sets of real-time quantity data; the near-infrared spectrometer and laser particle size analyzer collect the composition and particle size distribution data of the clean coal, forming multiple sets of real-time quality data.

[0164] The data and quality collection equipment for the dehydrator and filter also operates at the same collection frequency, generating multiple sets of real-time quantity and quality data. Through continuous collection, real-time data on quality and quantity of each key process link is accumulated.

[0165] Step S144: A multi-device data fusion mechanism is used to process the multiple sets of real-time quantity and quality data. The multi-device data fusion mechanism generates fused real-time quantity data and real-time quality data by performing weighted average calculations on the real-time quantity data and the real-time quality data, respectively, and combining the acquisition accuracy weights of each quantity and quality acquisition device in quantity and quality.

[0166] For multiple sets of real-time quantitative data from the dense medium separator (derived from electromagnetic flowmeters and vortex flowmeters), we first determined the accuracy weights for each device. Based on the device's calibration reports and a comparison of historical data, the electromagnetic flowmeter had higher measurement accuracy than the vortex flowmeter under these operating conditions. Therefore, the electromagnetic flowmeter was assigned a higher weight, while the vortex flowmeter was assigned a lower weight.

[0167] Multiply the multiple sets of real-time quantity data collected by the electromagnetic flowmeter with the corresponding weights, then multiply the multiple sets of real-time quantity data collected by the vortex flowmeter with the corresponding weights, then add the two product results, and finally divide them by the sum of the two weights to obtain the real-time quantity data after fusion of the heavy medium separator.

[0168] For the multiple sets of real-time quality data from the dense medium separator (derived from an online ash analyzer and an X-ray fluorescence analyzer), the accuracy weights for each collection device are similarly determined. The online ash analyzer, which has greater accuracy in detecting clean coal ash content, is assigned a larger weight. The X-ray fluorescence analyzer is assigned a corresponding weight based on its elemental analysis accuracy. The multiple sets of real-time quality data from the online ash analyzer are multiplied by the weights, and the multiple sets of real-time quality data from the X-ray fluorescence analyzer are multiplied by the weights. The two products are added and divided by the sum of the two weights to obtain the fused real-time quality data from the dense medium separator.

[0169] For multiple sets of real-time quantity and quality data from flotation machines, dewatering machines, and filters, the same processing method as that of heavy medium separators is adopted. The weights are determined according to the collection accuracy of each device, and weighted average calculations are performed to generate the fused real-time quantity data and real-time quality data.

[0170] Step S145: Extract the theoretical quantity and quality data corresponding to the key process link from the theoretical quantity and quality data of each process link, compare the fused real-time quantity data with the corresponding theoretical quantity data, and calculate the quantity deviation value; compare the fused real-time quality data with the corresponding theoretical quality data, and calculate the quality deviation value.

[0171] From the theoretical quantity and quality data for each process step generated by the process flow model, the corresponding theoretical quantity and quality data for the key process steps (heavy medium separator, flotation cell, dewatering machine, and filter) were selected. The theoretical quantity data for the heavy medium separator is the theoretical value of the clean coal volume flow rate calculated by the model, and the theoretical quality data is the theoretical value of the clean coal ash content and elemental composition. The theoretical quantity data for the flotation cell is the theoretical value of the flow rate of the floated clean coal, and the theoretical quality data is the theoretical value of the clean coal composition and particle size distribution. The theoretical quantity data for the dewatering machine is the theoretical value of the delivery volume of the dewatered clean coal, and the theoretical quality data is a theoretical description of the moisture content and physical state of the clean coal. The theoretical quantity data for the filter is the theoretical value of the flow rate of the filtered material, and the theoretical quality data is the theoretical value of the moisture content and viscosity of the material.

[0172] For the dense medium separator, the fused real-time quantity data (fused volume flow data) is compared with the corresponding theoretical quantity data (theoretical volume flow value), and the difference between the two is calculated to obtain the dense medium separator's quantity deviation value. Simultaneously, the fused real-time quality data (fused value of ash content and elemental composition) is compared with the theoretical quality data (theoretical value of ash content and elemental composition), and the difference is calculated to obtain the dense medium separator's quality deviation value.

[0173] The same method is used to calculate the quantity deviation and quality deviation of the flotation machine, dewatering machine, and filter respectively. That is, by comparing the fused real-time quantity and quality data with the corresponding theoretical quantity and quality data, the deviation value of each key process link is obtained.

[0174] Step S146: According to the connection relationship and material transfer sequence of each key process link, the transmission path of the deviation between each process link is tracked to generate the deviation propagation path information, and the quantity deviation value, quality deviation value and deviation propagation path information are combined to generate the quantity and quality deviation analysis results.

[0175] Step S1461: Compare the real-time quantity data and theoretical quantity data of the same key process link, and use the absolute deviation calculation method to calculate the quantity deviation value, which is the absolute value of the difference between the real-time quantity data and the theoretical quantity data.

[0176] Taking a dense medium separator as an example, obtain the fused real-time quantity data (such as the volume flow rate at a certain moment) and the corresponding theoretical quantity data (the theoretical volume flow rate at the same moment). Using the absolute deviation calculation method, subtract the theoretical quantity data from the real-time quantity data and then take the absolute value of the difference to obtain the quantity deviation value of the dense medium separator at that moment.

[0177] The same absolute deviation calculation method is used for flotation machines, dewatering machines, and filters. The corresponding theoretical quantity data is subtracted from the fused real-time quantity data, and the absolute value of the difference is taken to obtain the quantity deviation value for each key process link. The quantity deviation value calculated in this way intuitively reflects the degree of deviation between the real-time quantity data and the theoretical quantity data.

[0178] Step S1462: Compare the real-time quality data of the same key process link with the theoretical quality data, and select the corresponding deviation calculation method according to the type of quality data. If the quality data is component content data, the relative deviation calculation method is used to calculate the quality deviation value, and the quality deviation value is the absolute value of the ratio to the theoretical quality data; if the quality data is state data, the quality deviation value is calculated through state matching evaluation, and the state matching evaluation outputs the deviation value by comparing the degree of conformity between the real-time state and the theoretical state.

[0179] The quality data (clean coal ash content and elemental composition) of the dense medium separator is classified as component content data and is calculated using a relative deviation method. The difference is calculated by subtracting the theoretical mass data from the fused real-time mass data. This difference is then divided by the theoretical mass data, and the absolute value of the result is taken to obtain the mass deviation value (mass deviation value) of the dense medium separator.

[0180] In the quality data of the flotation machine, the clean coal composition belongs to the component content data, and the deviation value is calculated using the above-mentioned relative deviation calculation method; although the particle size distribution is numerical data, it focuses more on the distribution state. The deviation value is calculated through state matching evaluation, and the real-time particle size distribution is compared with the theoretical particle size distribution to analyze the degree of compliance between the two. The lower the degree of compliance, the greater the deviation value.

[0181] In the quality data of the dehydrator, the moisture content of clean coal belongs to the component content data, and the relative deviation calculation method is used; the physical state is obtained through image analysis and belongs to the state data. The deviation value is calculated by comparing the matching degree between the real-time physical state and the theoretical physical state.

[0182] The quality data processing method of the filter is similar. The moisture is calculated using relative deviation, and the viscosity selects the appropriate deviation calculation method based on its characteristics to ensure that the quality deviation value can accurately reflect the difference between the real-time quality and the theoretical quality.

[0183] The transmission between nodes. For example, after the quantity deviation value of the heavy medium separator is substituted into the model, the model will calculate the value of the deviation transmitted to the dehydrator based on the material transfer ratio between it and the dehydrator. It then determines whether the dehydrator will generate new quantity deviations or aggravate the existing deviations. In this way, the transmission path of the quantity deviation from the initial process link to the subsequent process links is tracked.

[0184] The mass deviation value is also substituted into the mass deviation propagation path model. After the mass deviation value of the dense medium separator is entered into the model, the model analyzes the impact of the mass deviation on the dehydrator's processing performance based on the quality impact relationship between the mass deviation and the dehydrator, calculates the mass deviation value transmitted to the dehydrator, and tracks the mass deviation's transmission path.

[0185] The flotation machine's quantity and quality deviation values ​​are also substituted into their corresponding deviation propagation path models in the same manner as above, tracking their transmission to the filter. By integrating the transmission paths of all quantity and quality deviations, the starting point, transmission nodes, and ultimate impact range of each deviation are determined, generating the final deviation propagation path information.

[0186] Step S1464: Organize the identification information, real-time quantity data, theoretical quantity data, quantity deviation value, real-time quality data, theoretical quality data, quality deviation value and deviation propagation path information of each key process link into a structured data format.

[0187] Collect identification information for each key process link (heavy medium separator, flotation machine, dewatering machine, filter), such as equipment number and name. Also, summarize real-time quantity data, theoretical quantity data, quantity deviation values, as well as real-time quality data, theoretical quality data, and quality deviation values ​​for each key process link.

[0188] This information, along with the deviation propagation path information, is organized and stored in a structured data format. For example, the name and content of each field should be clearly defined, such as "Equipment number: XXX, Equipment name: Heavy medium separator, Real-time quantity data: XXX, Theoretical quantity data: XXX, Quantity deviation value: XXX, Real-time quality data: XXX, Theoretical quality data: XXX, Quality deviation value: XXX, Deviation propagation path: XXX." This structured processing makes the data clearly organized and facilitates subsequent analysis and use.

[0189] Step S1465: Set a quantity deviation threshold and a quality deviation threshold, compare the quantity deviation value of each key process link with the quantity deviation threshold, and compare the quality deviation value with the quality deviation threshold to determine the deviation exceeding tolerance of each key process link.

[0190] Quantity deviation thresholds and quality deviation thresholds are set based on the production standards and process requirements of the process plant. The quantity deviation threshold determines whether the quantity deviation exceeds the acceptable range, while the quality deviation threshold determines whether the quality deviation exceeds the tolerance.

[0191] Compare the quantity deviation value of the dense medium separator with the quantity deviation threshold. If the quantity deviation value is greater than the quantity deviation threshold, the quantity deviation of this process step is determined to be out of tolerance; otherwise, it is within tolerance. Similarly, compare its quality deviation value with the quality deviation threshold to determine whether the quality deviation is out of tolerance.

[0192] Using the same method, the quantity deviation values ​​and quality deviation values ​​of the flotation machine, dewatering machine, and filter are compared with the corresponding thresholds, and the deviation exceeding the tolerance of each key process link is determined one by one, such as which links have quantity exceeding the tolerance, which links have quality exceeding the tolerance, and which links have both quantity and quality exceeding the tolerance.

[0193] Step S1466: Integrate the structured data, the deviation and tolerance conditions of each key process link, and the deviation threshold information to generate a number and quality deviation analysis result. The number and quality deviation analysis result also includes a description of the method used for deviation calculation and data collection time information.

[0194] The organized structured data, the deviation and tolerance conditions of each key process link (such as the quantity deviation of the heavy medium separator, the quality deviation of the flotation machine, etc.), and the set quantity deviation threshold and quality deviation threshold information are integrated.

[0195] During the integration process, a description of the method used to calculate the deviation is added, such as the absolute deviation calculation method for quantity deviation and the relative deviation calculation method for component content quality deviation, etc. At the same time, the time information of data collection is recorded, including year, month, day, hour, minute and second.

[0196] Through the above integration, a complete number and quality deviation analysis result is formed, which presents the number and quality deviation situation, out-of-tolerance status, calculation method, data source time and other information of each key process link.

[0197] Step S150: Generate a process parameter adjustment instruction based on the data and mass deviation analysis result, and send the process parameter adjustment instruction to the control terminal of the process plant to adjust the operating parameters of the corresponding process link. The process parameter adjustment instruction includes adjustment effect prediction information.

[0198] Detailed interpretation of the logarithmic mass deviation analysis results will clarify the deviation type (quantity deviation or quality deviation), deviation magnitude, and deviation propagation path for each key process step. Based on this information, the process steps and corresponding operating parameters that require adjustment are determined, such as the separation density of the dense medium separator and the reagent dosage of the flotation machine.

[0199] By analyzing the correlation between deviations and operating parameters, specific adjustments can be calculated, such as how much to adjust the separation density of a dense medium separator or how much to increase or decrease the reagent dosage of a flotation machine. Furthermore, the change in deviation after adjustment is predicted, i.e., the adjustment effect prediction information, such as the estimated reduction in quantity deviation and the degree to which quality deviation can be reduced.

[0200] The identification of the process link that needs to be adjusted, the type of operating parameters, the specific adjustment amount and the adjustment effect prediction information are integrated to form a process parameter adjustment instruction, and then the instruction is sent to the control terminal of the process plant to adjust the operating parameters of the corresponding process link.

[0201] Step S151: parse the quantity deviation value, quality deviation value and deviation propagation path information in the quantity and quality deviation analysis result to determine the key process link and deviation type corresponding to the deviation, wherein the deviation type includes quantity deviation type and quality deviation type.

[0202] The results of the logarithmic and mass deviation analysis are disassembled to extract the quantity deviation value and quality deviation value. At the same time, the deviation propagation path information is analyzed to trace the source and impact range of the deviation.

[0203] According to the process link identification corresponding to the deviation value, the key process link corresponding to each deviation is determined, such as a certain quantity deviation value corresponds to a heavy medium separator, a certain quality deviation value corresponds to a flotation machine, etc.

[0204] The deviation type is distinguished based on the content reflected by the deviation value. If the deviation value is for the material quantity index (such as flow rate, conveying volume), it is determined to be a quantity deviation type; if the deviation value is for the material quality index (such as ash content, moisture, composition), it is determined to be a quality deviation type.

[0205] Step S152: Based on the deviation type and deviation size, call the preset parameter adjustment rule library to determine the type and adjustment direction of the operating parameters that need to be adjusted for the corresponding key process links. The operating parameter type includes the types of process parameters that affect the quantity and quality of material processing.

[0206] The preset parameter adjustment rule base stores the corresponding rules for different deviation types and sizes and operating parameter adjustments. For example, if a large quantity deviation occurs in the dense medium separator, the rule base stipulates that its feed rate needs to be adjusted; if a small quality deviation occurs (ash content exceeds the standard), the separation density needs to be adjusted.

[0207] Based on the deviation type (quantity deviation or quality deviation) and deviation size obtained through analysis, the corresponding rules are called from the parameter adjustment rule library to determine the type of operating parameters that need to be adjusted in the corresponding key process links, such as the feed rate and sorting density of the heavy medium separator, the reagent dosage and slurry concentration of the flotation machine, etc.

[0208] At the same time, the adjustment direction is determined according to the direction of the deviation (such as quantity is too much or too little, quality exceeds or is insufficient), such as the feed speed needs to be reduced or increased, the sorting density needs to be increased or decreased, etc.

[0209] Step S153: Based on the adjustment direction and the deviation size, a specific adjustment amount of the operating parameter to be adjusted is calculated by a parameter optimization algorithm. The parameter optimization algorithm can output a parameter adjustment amount that reduces the deviation according to the deviation situation.

[0210] For example, step S1531: the adjustment direction, deviation size and current operating parameter value of the corresponding key process link are used as input data of the parameter optimization algorithm, and the constraint range of the operating parameters of the key process link is determined at the same time, and the constraint range includes the maximum and minimum allowable values ​​of the operating parameters.

[0211] Taking a dense medium separator as an example, the parameter optimization algorithm inputs the adjustment direction (e.g., reducing the separation density), the magnitude of the quality deviation (e.g., an excessively high ash content), and the current separation density value. Simultaneously, based on the dense medium separator's equipment performance and process requirements, the separation density constraint range—that is, the maximum and minimum allowable values—is determined. For example, the separation density cannot be lower than or higher than a certain value.

[0212] For flotation machines, if the adjustment direction is to increase the reagent dosage, the adjustment direction, the corresponding deviation size and the current reagent dosage value are input into the algorithm, and the maximum and minimum allowable reagent dosage values ​​are determined as the constraint range to ensure that the adjusted reagent dosage is within the range allowed by the equipment and process.

[0213] Step S1532: Initialize the iteration parameters of the parameter optimization algorithm, the iteration parameters including the upper limit of the number of iterations, the convergence threshold and the initial search step size, the convergence threshold being the standard for reducing the deviation to an acceptable range.

[0214] Set the upper limit of the number of iterations of the parameter optimization algorithm. The upper limit of the number of iterations is determined according to the process complexity and calculation accuracy requirements. For example, it is set to dozens of times to avoid the algorithm falling into infinite iterations.

[0215] Determine a convergence threshold. When the deviation decreases below this threshold, the deviation is considered to be within an acceptable range and the algorithm can stop iterating. For example, the convergence threshold can be set to a certain ratio of the initial deviation. When the adjusted deviation is less than the value corresponding to this ratio, the convergence condition is met.

[0216] Set the initial search step size. The step size is determined by the adjustment sensitivity of the operating parameters. For example, the initial search step size of the sorting density is a fixed value, and the initial search step size of the reagent dosage is another fixed value. Too large a step size may lead to excessive adjustment, while too small a step size may extend the iteration time.

[0217] Step S1533: generating a plurality of candidate operating parameter adjustment amounts within the constraint range of the operating parameter according to the adjustment direction and the initial search step size.

[0218] Within the constraints of the dense medium separator's sorting density, multiple candidate adjustment variables are generated based on the adjustment direction for reducing the sorting density and the initial search step size. For example, if the current sorting density is a certain value and the initial search step size is a certain value, the candidate adjustment variables could be the current value minus one step size, minus two step sizes, and so on. These candidate adjustment variables must all be between the maximum and minimum allowable values.

[0219] For the reagent dosage adjustment of the flotation machine, within its constraint range, multiple candidate adjustment amounts are generated according to the direction of increasing the reagent dosage and the initial search step size, such as the current dosage plus one step size, plus two step sizes, etc., to ensure that the candidate adjustment amounts are within the constraint range.

[0220] Step S1534: Substitute each candidate adjustment value of the operating parameter into the process flow model, simulate and calculate the changes in the theoretical quantitative and qualitative data of the corresponding key process links, and obtain the simulated deviation value corresponding to each candidate adjustment value.

[0221] Each candidate adjustment amount of the heavy medium separator for separation density is substituted into the process flow model. The model will simulate the operating state of the heavy medium separator under the separation density, calculate the corresponding theoretical quantitative and qualitative data (such as the ash content of clean coal), and then compare the data with the theoretical target value to obtain the simulated deviation value corresponding to each candidate adjustment amount.

[0222] Similarly, each candidate adjustment amount of the reagent dosage of the flotation machine is substituted into the model, and the corresponding theoretical quantitative and qualitative data changes are simulated and calculated to obtain the respective simulation deviation values.

[0223] Step S1535: introducing simulation deviation value stability assessment, calculating the fluctuation range of the simulation deviation value corresponding to each candidate adjustment amount in multiple consecutive simulation calculations, and screening out candidate adjustment amounts with fluctuation ranges less than a preset fluctuation threshold.

[0224] Each candidate adjustment value for the dense medium separator is repeatedly substituted into the process model for simulation calculations to obtain multiple simulated deviation values. The differences between these simulated deviation values, such as the difference between the maximum and minimum values, are calculated. This difference is the fluctuation amplitude.

[0225] A preset fluctuation threshold is set. If the fluctuation amplitude of a candidate adjustment amount is less than the threshold, it means that the simulation deviation value corresponding to the adjustment amount is relatively stable and it will be retained; otherwise, the candidate adjustment amount will be eliminated.

[0226] The same stability evaluation and screening are also performed on the candidate adjustment amounts of the flotation machine to ensure that the retained candidate adjustment amounts have a stable adjustment effect.

[0227] Step S1536: Compare the simulated deviation values ​​corresponding to the selected candidate adjustment amounts with the current deviation value, and select the candidate adjustment amount that makes the simulated deviation value smaller than the current deviation value as the valid candidate adjustment amount.

[0228] Compare the simulated deviation values ​​corresponding to the candidate adjustment amounts of each sorting density after screening by the heavy medium separator with the current mass deviation value. If the simulated deviation value of a candidate adjustment amount is smaller than the current deviation value, it indicates that the adjustment amount can reduce the deviation and is determined as a valid candidate adjustment amount.

[0229] The candidate adjustment amounts screened by the flotation machine are compared with the current deviation value in the same way to screen out valid candidate adjustment amounts.

[0230] Step S1537: Select the valid candidate adjustment amount that minimizes the simulation deviation value as the current optimal adjustment amount. If the simulation deviation value corresponding to the current optimal adjustment amount is less than the convergence threshold, the current optimal adjustment amount is used as the final adjustment amount; if it is greater, adjust the search step size, and repeat the steps of generating candidate adjustment amounts, calculating simulation deviation values, performing stability evaluation and screening valid candidate adjustment amounts until the number of iterations reaches the upper limit or the simulation deviation value is less than the convergence threshold.

[0231] From the available candidate adjustment variables for the dense medium separator, the one with the smallest simulated deviation is selected as the current optimal separation density adjustment variable. If the simulation deviation corresponding to the optimal adjustment variable is less than the convergence threshold, it is determined as the final separation density adjustment variable.

[0232] If the simulation deviation is greater than the convergence threshold, the search step size is adjusted, for example, by reducing it to half its original value. Within the constraints, candidate adjustment variables are regenerated using the new step size and adjustment direction. Simulation calculations, stability assessments, and valid candidate adjustment variable screening are performed again. This process repeats until the number of iterations reaches the set upper limit or the simulation deviation is less than the convergence threshold.

[0233] The process of determining the optimal adjustment amount of the flotation machine is the same as that of the dense medium separator. The final effective adjustment amount is obtained through iterative calculation and step size adjustment.

[0234] Step S1538: If there is no valid candidate adjustment amount, adjust the fine-tuning amplitude of the adjustment direction, regenerate the candidate adjustment amount of the operating parameter, and perform the simulation calculation, stability evaluation and screening steps again until the final adjustment amount that meets the requirements is obtained, and use the final adjustment amount as the specific adjustment amount of the operating parameter that needs to be adjusted.

[0235] If no valid candidate adjustment variables exist for the dense medium separator, meaning that the simulated deviations corresponding to all candidate adjustment variables are not less than the current deviation, the adjustment direction is fine-tuned. For example, if the original adjustment direction was to significantly reduce the separation density, the fine-tuning is to slightly reduce the separation density. Then, new candidate adjustment variables are generated based on the fine-tuned direction.

[0236] After that, the simulation calculation, stability assessment, and effective candidate adjustment amount screening steps are repeated. If there are still no effective candidate adjustment amounts, the adjustment direction is fine-tuned, such as slightly increasing the separation density, regenerating candidate adjustment amounts, and performing related steps until the final adjustment amount that meets the requirements is obtained. This is used as the specific adjustment amount for the operating parameters of the dense medium separator.

[0237] If a similar situation occurs in the flotation machine, the fine-tuning amplitude of the adjustment direction is also adjusted in the above manner, and the candidate adjustment amount is regenerated and processed until the final adjustment amount is determined.

[0238] Step S154: Substitute the key process link identifier, the type of operating parameter that needs to be adjusted, and the specific adjustment amount into the process flow model, simulate the operating status of the adjusted process link, obtain the adjusted simulated digital quality data, calculate the deviation reduction between the adjusted simulated digital quality data and the theoretical digital quality data, and use the deviation reduction as the adjustment effect prediction information.

[0239] Substitute the identification of the heavy medium separator, the type of operating parameter that needs to be adjusted (such as sorting density), and the specific adjustment amount into the process flow model. The model will simulate the operating status of the heavy medium separator under the new sorting density and output the adjusted simulated quantity data and simulated quality data.

[0240] Calculate the deviation between these adjusted simulated mass data and the corresponding theoretical mass data, compare it with the deviation before adjustment, and obtain the deviation reduction amplitude. For example, if the mass deviation before adjustment is a certain value and another value after adjustment, the ratio of the difference between the two and the deviation before adjustment is the deviation reduction amplitude. The deviation reduction amplitude is used as the prediction information of the adjustment effect.

[0241] For key process links that need to be adjusted, such as flotation machines, dewatering machines, and filters, the above method is used to obtain their respective adjustment effect prediction information.

[0242] Step S155: Integrate the key process link identifier, the type of operating parameter to be adjusted, the specific adjustment amount and the adjustment effect prediction information to generate a process parameter adjustment instruction, which includes format information for communicating with the control terminal.

[0243] Summarize the identification of each key process link that needs to be adjusted (such as equipment number), the type of operating parameter that needs to be adjusted (such as sorting density, reagent dosage), the specific adjustment amount (such as how much the sorting density is reduced, how much the reagent dosage is increased), and the corresponding adjustment effect prediction information (such as the deviation reduction range).

[0244] This information is encapsulated according to the communication format agreed upon with the control terminal. The communication format information includes the data transmission protocol type, data packet structure, verification method, etc., to ensure that the control terminal can correctly receive and parse the instruction content and generate process parameter adjustment instructions.

[0245] Step S156: Send the process parameter adjustment instruction to the control terminal of the process plant.

[0246] The generated process parameter adjustment instructions are sent to the corresponding control terminal via the industrial Ethernet or dedicated communication lines within the process plant. After receiving the instructions, the control terminal parses them, extracting information such as the key process link identifier, operating parameter type, and specific adjustment amount. Then, the control terminal adjusts the operating parameters of the corresponding process link according to the instructions to achieve optimized control of the process.

[0247] Figure 2 A schematic diagram illustrates exemplary hardware and software components of a system 100 for implementing a digital twin of a process plant based on dynamic data quality analysis, according to some embodiments of the present application. For example, a processor 120 may be used in the system 100 for implementing a digital twin of a process plant based on dynamic data quality analysis and for executing the functions described herein.

[0248] For example, the digital twin implementation system 100 of a process plant based on dynamic data quality analysis may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and storage media 140 in different forms, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the digital twin implementation system 100 of a process plant based on dynamic data quality analysis may also include program instructions stored in ROM, RAM, or other types of non-temporary storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The digital twin implementation system 100 of a process plant based on dynamic data quality analysis also includes an I / O interface 150 between the computer and other input and output devices.

[0249] In addition, an embodiment of the present invention also provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned process plant digital twin implementation method based on dynamic data quality analysis is implemented.

[0250] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, multiple features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A method for implementing digital twins of process plants based on dynamic data quality analysis, characterized in that: The method comprises: Obtaining process link characteristic data and initial material input data of the process plant, wherein the process link characteristic data includes regular information on how each process link implements material processing functions, and the initial material input data includes basic attribute information of the materials; A process flow model is constructed based on the process link characteristic data and the initial material input data. The process flow model is used to reflect the connection relationship between each process link and the material transfer relationship between each process link. The process flow model can receive the material input data and output the material processing result data of the corresponding process link; Performing a process simulation calculation based on the process flow model and the initial material input data to obtain theoretical quantity and quality data for each process link, wherein the theoretical quantity and quality data include quantity information and quality information of the output material of each process link, and introducing a material property transfer attenuation coefficient into the process of the process flow simulation calculation; Collecting real-time data on quality and quality of each key process link in the process plant, processing the real-time data using a multi-device data fusion mechanism, and comparing and analyzing the processed real-time data with the theoretical data and quality of the corresponding process link to obtain a data and quality deviation analysis result, which includes information on the deviation propagation path; A process parameter adjustment instruction is generated based on the data and mass deviation analysis result, and the process parameter adjustment instruction is sent to the control terminal of the process plant to adjust the operating parameters of the corresponding process link. The process parameter adjustment instruction includes adjustment effect prediction information.

2. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 1 is characterized in that: The process flow model is constructed based on the process link characteristic data and initial material input data, including: Classify and organize the characteristic data of the process links and extract the material processing regularity information of each process link, wherein the material processing regularity information includes the change rules of the input material after being processed by the process link and converted into the output material; According to the actual production process of the process plant, the material transfer sequence between each process link is determined to form a process link transfer relationship list, which records the corresponding relationship between the input port and the output port of the adjacent process links; Call the process flow modeling tool, drag and drop the graphic symbols corresponding to each process link according to the process link transfer relationship list, establish connecting lines between the graphic symbols of each process link to represent the material transfer path, and preliminarily build the process flow model framework; Encapsulate the material handling rule information of each process link into the corresponding process link graphic symbol, and set a parameter configuration interface for the process flow model framework, wherein the parameter configuration interface can receive external input process parameter adjustment data; Establish a dynamic update interface for process link characteristics, which can receive real-time collected process link operation status data and update the material processing regularity information of the corresponding process link according to the process link operation status data; Input the initial material input data into the parameter configuration interface, trigger the process flow model framework to perform material processing simulation according to the material processing rule information of each process link, generate simulation output data of each process link, and complete the construction of the process flow model.

3. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 2 is characterized in that: The process step characteristic data is classified and sorted to extract the material processing regularity information of each process step, including: Classifying the process link characteristic data according to the function type of the process link, wherein the function type includes a material mixing function type, a material separation function type, and a material transportation function type; For each type of process characteristic data, extract information describing the corresponding relationship between material input attributes, processing parameters, and output attributes. The input attributes include the composition and state information of the material, the processing parameters include the operating parameters when the process is running, and the output attributes include the composition and state information of the processed material. Optimize the correspondence information between the extracted input attributes, processing parameters and output attributes, remove duplicate and contradictory information, and form a preliminary material processing relationship data set; Based on the preliminary material processing relationship data set, through data fitting and rule induction, a change rule is constructed to transform the input material into the output material after being processed in the process link. The change rule is used to clarify the output attribute corresponding to the combination of input attributes and processing process parameters; Setting a dynamic correction factor for the change rule, wherein the dynamic correction factor can be adjusted according to the operation time of the process link and maintenance records; The change rules are associated with the identification information of the corresponding process links to form the material processing regularity information of each process link, and the format of the material processing regularity information is standardized at the same time.

4. The method for implementing a digital twin of a process plant based on dynamic data quality analysis according to claim 1 is characterized in that: The process flow simulation calculation is performed based on the process flow model and the initial material input data to obtain theoretical quantitative and qualitative data of each process link, including: Inputting the initial material input data into the process flow model through the parameter configuration interface of the process flow model, and determining the starting process link corresponding to the initial material input data; Using the process flow model, starting from the starting process link in the order of the process link transfer relationship list, calling the material processing rule information encapsulated in the process link to process the input initial material input data, and generating the intermediate material output data of the starting process link; Determine the material property transfer attenuation coefficient based on the material transfer distance and transfer method between process links. The material property transfer attenuation coefficient includes the material quantity transfer attenuation coefficient and the material quality property attenuation coefficient, which is used to correct the property loss of the material during the transfer process; The quantity information in the intermediate material output data of the starting process link is attenuated and corrected using the material quantity transfer attenuation coefficient, and the quality information in the intermediate material output data of the starting process link is attenuated and corrected using the material quality attribute attenuation coefficient to obtain corrected intermediate material output data. The corrected intermediate material output data is used as input data for the next process link, and the material processing rule information encapsulated in the next process link is called for processing to generate the intermediate material output data of the next process link. Repeat the above steps of determining the material property transfer attenuation coefficient, performing attenuation correction on the intermediate material output data of the previous process link and processing it as input data for the next process link until the material handling simulation of all process links is completed and the final material output data of the final process link is obtained; The intermediate material output data generated by each process link and the final material output data of the final process link are sorted out, and the quantity information and quality information are extracted to form the theoretical quantity and quality data of each process link.

5. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 4 is characterized in that: The process flow model starts from the starting process link in the order of the process link transfer relationship list, calls the material processing rule information encapsulated in the process link to process the input initial material input data, and generates the intermediate material output data of the starting process link, including: The process flow model reads the process link transfer relationship list to determine the identification of the starting process link and the storage path of the material processing rule information corresponding to the starting process link; The material processing rule information encapsulated in the initial process link is called through the storage path, and the material processing change rule and dynamic correction factor therein are loaded; Converting the inputted initial material input data into the format required by the material processing rule information, extracting the input attribute information in the initial material input data, and matching it with the input attribute items in the material processing change rule; Determine the default values ​​of the process parameters for the current running state of the starting process link based on the matched input attribute information and the material processing change rules. If the initial material input data contains process parameter adjustment information, replace the default values ​​of the process parameters with the parameter values ​​in the adjustment information. Based on the matched input attribute information, the determined processing parameter values ​​and the dynamic correction factor, the material processing change rules are substituted for calculation to obtain the output attribute information of the material after the processing of the starting process link; The material output attribute information is associated with the starting process link identifier and processing time information to generate intermediate material output data of the starting process link, and the intermediate material output data is stored in the temporary data storage module of the process flow model.

6. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 1 is characterized in that: The real-time data of the key process links of the process plant are collected, and after processing the real-time data of ... According to the process flow and product composition of the process plant, determine the key process links that have a direct impact on the quantity and quality of the final product, and form a list of key process links; For each key process link in the key process link list, select at least two suitable data and quality collection devices, wherein the data and quality collection devices are used to collect real-time quantity information and real-time quality information of the output material of the corresponding key process link; The data and quality collection device is started to collect real-time quantity information and real-time quality information of the output materials of each key process link according to a preset collection frequency, so as to obtain multiple sets of real-time data of data and quality of each key process link; The multiple sets of real-time quantity and quality data are processed using a multi-device data fusion mechanism, wherein the multi-device data fusion mechanism generates fused real-time quantity data and real-time quality data by performing weighted average calculations on the real-time quantity data and the real-time quality data, and combining the acquisition accuracy weights of each data and quality acquisition device in terms of quantity and quality; Extract the theoretical quantity and quality data corresponding to the key process link from the theoretical quantity and quality data of each process link, compare the fused real-time quantity data with the corresponding theoretical quantity data, and calculate the quantity deviation value; compare the fused real-time quality data with the corresponding theoretical quality data, and calculate the quality deviation value; According to the connection relationship and material transfer sequence of each key process link, the transmission path of the deviation between each process link is tracked to generate the deviation propagation path information, and the quantity deviation value, quality deviation value and deviation propagation path information are combined to generate the quantity and quality deviation analysis results.

7. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 6 is characterized in that: According to the process flow and product composition of the process plant, determine the key process links that have a direct impact on the quantity and quality of the final product, and form a list of key process links, including: Based on the complete process flow of the process plant, draw a process flow diagram, and identify the input and output ports of each process link and the material transfer paths between each process link in the process flow diagram; Analyze the components of the final product and determine the material branches that make up the final product. The material branch is the sequence of process links that the material goes through from the initial material input to the final product output; For each material branch, from the initial process link to the final process link, the degree of influence of the output material of each process link on the material processing results of the subsequent process link is analyzed in turn, and the influence factor value of each process link is calculated using the influence factor evaluation method. The influence factor value represents the degree of influence of the process link on the subsequent material processing results; Select the process links in each material branch whose impact factor value is greater than the impact factor threshold as candidate key process links for the material branch; Summarize the candidate key process links of all material branches, remove duplicate process links, mark each candidate key process link with its material branch and influencing factor value, and form a list of key process links; The historical data of process link failures are introduced to prioritize the candidate key process links in the key process link list. The candidate key process links with higher failure frequencies are ranked higher, and the key process link list is updated.

8. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 6 is characterized in that: The method comprises comparing the fused real-time quantity data with the corresponding theoretical quantity data to calculate the quantity deviation value; comparing the fused real-time quality data with the corresponding theoretical quality data to calculate the quality deviation value, and generating a quantity and quality deviation analysis result based on the quantity deviation value, the quality deviation value and the deviation propagation path information, including: Compare the real-time quantity data and theoretical quantity data of the same key process link, and calculate the quantity deviation value using the absolute deviation calculation method, wherein the quantity deviation value is the absolute value of the difference between the real-time quantity data and the theoretical quantity data; Compare the real-time quality data of the same key process link with the theoretical quality data, and select the corresponding deviation calculation method according to the type of quality data. If the quality data is component content data, the relative deviation calculation method is used to calculate the quality deviation value, and the quality deviation value is the absolute value of the ratio with the theoretical quality data; if the quality data is state data, the quality deviation value is calculated through state matching evaluation, and the state matching evaluation outputs the deviation value by comparing the degree of conformity between the real-time state and the theoretical state; According to the connection sequence and material transfer relationship of each key process link in the process flow, a deviation propagation path model is constructed. The quantity deviation value of each key process link is substituted into the quantity deviation propagation path model to track the transmission path of the quantity deviation from the initial process link to the subsequent process link. The quality deviation value of each key process link is substituted into the quality deviation propagation path model to track the transmission path of the quality deviation from the initial process link to the subsequent process link. The propagation path information of the quantity deviation and the quality deviation is integrated to generate the final deviation propagation path information. Organize the identification information, real-time quantity data, theoretical quantity data, quantity deviation value, real-time quality data, theoretical quality data, quality deviation value and deviation propagation path information of each key process link into a structured data format; Setting a quantity deviation threshold and a quality deviation threshold, comparing the quantity deviation value of each key process link with the quantity deviation threshold, and comparing the quality deviation value with the quality deviation threshold, to determine the deviation out-of-tolerance situation of each key process link; The structured data, deviation out-of-tolerance conditions of each key process link, and deviation threshold information are integrated to generate a number and quality deviation analysis result. The number and quality deviation analysis result also includes a description of the method used for deviation calculation and data collection time information.

9. The method for realizing digital twin of process plant based on dynamic data quality analysis according to claim 1 is characterized in that: Generating a process parameter adjustment instruction according to the data and mass deviation analysis result, and sending the process parameter adjustment instruction to a control terminal of a process plant to adjust the operating parameters of a corresponding process link, includes: Analyze the quantity deviation value, quality deviation value and deviation propagation path information in the quantity and quality deviation analysis result, and determine the key process link and deviation type corresponding to the deviation, wherein the deviation type includes quantity deviation type and quality deviation type; Based on the deviation type and deviation size, the preset parameter adjustment rule library is called to determine the type and direction of the operating parameters that need to be adjusted for the corresponding key process links. The operating parameter type includes the types of process parameters that affect the quantity and quality of material processing; Based on the adjustment direction and the deviation size, a parameter optimization algorithm is used to calculate a specific adjustment amount of the operating parameter that needs to be adjusted. The parameter optimization algorithm can output a parameter adjustment amount that reduces the deviation according to the deviation situation; Substituting the key process link identifier, the type of operating parameter to be adjusted, and the specific adjustment amount into the process flow model, simulating the operating state of the process link after adjustment, obtaining the adjusted simulated numerical quality data, calculating the reduction in deviation between the adjusted simulated numerical quality data and the theoretical numerical quality data, and using the reduction in deviation as adjustment effect prediction information; Integrate the key process link identifier, the type of operating parameter to be adjusted, the specific adjustment amount, and the adjustment effect prediction information to generate a process parameter adjustment instruction, wherein the process parameter adjustment instruction includes format information for communication with the control terminal; The process parameter adjustment instruction is sent to the control terminal of the process plant.

10. A digital twin implementation system for a process plant based on dynamic data quality analysis, characterized in that: It includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the process plant digital twin implementation method based on dynamic data quality analysis as described in any one of claims 1 to 9.

Images