Monitoring and early warning method and device for skid-mounted equipment

Abstract

The invention discloses a monitoring and early warning method and device for skid-mounted equipment, and relates to the technical field of monitoring and early warning, and the method comprises the steps: carrying out the function cooperation and fault influence causal relationship analysis according to a cooperation function block of the skid-mounted equipment, and constructing a causal association library; performing disassembling and clustering processing on the causal association library to obtain a clustering result and a corresponding relationship identifier; performing early warning path search based on the causal association library, and determining graded early warning information; and carrying out early warning monitoring on the collaborative functional blocks of the skid-mounted equipment according to the relationship identifier and the graded early warning information to obtain an early warning identification result. The technical problems of inaccurate monitoring and early warning, low safety and reliability and poor management efficiency caused by difficulty in comprehensively and accurately mastering the causal relationship of the skid-mounted equipment in the prior art are solved, and accurate monitoring and early warning of the running state of the skid-mounted equipment are realized; and the operation safety, reliability and management efficiency of the skid-mounted equipment are improved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and early warning technology, and in particular to a monitoring and early warning method and device for skid-mounted equipment. Background Art

[0002] Skid-mounted equipment plays a key role in many fields, such as petrochemicals, energy extraction, industrial manufacturing and other industries. It usually integrates multiple functional blocks, and each functional block works together to achieve a specific production process or task. However, with the increasing automation level and functional complexity of skid-mounted equipment, there are many challenges in operation. Traditional monitoring technology often only focuses on local parameters or a single functional block of the equipment, lacking an in-depth understanding and comprehensive analysis of the collaborative working relationship between the functional blocks and the causal relationship of the fault impact. This limitation makes it impossible to identify potential fault sources in a timely and accurate manner, and it is difficult to quickly locate the fault propagation path when a fault occurs, making it impossible to achieve effective early warning. Due to the lack of an accurate early warning mechanism, when a device fails, it may quickly spread to the entire system, triggering a chain reaction, seriously affecting the operational safety and reliability of the equipment.

[0003] The existing technology has the technical problem that it is difficult to fully and accurately grasp the cause and effect relationship of skid-mounted equipment, resulting in inaccurate monitoring and early warning, low safety and reliability, and poor management efficiency. Summary of the invention

[0004] The present application provides a monitoring and early warning method and device for skid-mounted equipment, which is used to solve the technical problem in the prior art that it is difficult to fully and accurately grasp the cause and effect relationship of skid-mounted equipment, resulting in inaccurate monitoring and early warning, low safety and reliability, and poor management efficiency.

[0005] In view of the above problems, the present application provides a monitoring and early warning method and device for skid-mounted equipment.

[0006] In a first aspect of the present application, a monitoring and early warning method for skid-mounted equipment is provided, the method comprising: According to the collaborative functional blocks of the skid-mounted equipment, functional collaboration and fault impact causal relationship analysis are performed to build a causal association library; the causal association library is disassembled and clustered according to the input data, data analysis, and result output logical framework to obtain clustering results and corresponding relationship identifiers, and the relationship identifiers include input relationship identifiers, processing relationship identifiers, and output relationship identifiers; according to the clustering results and corresponding relationship identifiers, a warning path search is performed based on the causal association library to determine the graded warning information; according to the relationship identifiers and the graded warning information, the collaborative functional blocks of the skid-mounted equipment are monitored for early warning, and early warning identification results are obtained.

[0007] A second aspect of the present application provides a monitoring and early warning device for skid-mounted equipment, the device comprising: A causal association library construction module is used to perform functional coordination and fault impact causal relationship analysis based on the collaborative functional blocks of the skid-mounted equipment to build a causal association library; a relationship identifier acquisition module is used to disassemble and cluster the causal association library according to the input data, data analysis, and result output logical framework to obtain clustering results and corresponding relationship identifiers, and the relationship identifiers include input relationship identifiers, processing relationship identifiers, and output relationship identifiers; a graded warning information determination module is used to perform warning path search based on the causal association library according to the clustering results and corresponding relationship identifiers, and determine graded warning information; a warning identification result acquisition module is used to perform warning monitoring of the collaborative functional blocks of the skid-mounted equipment according to the relationship identifiers and the graded warning information to obtain warning identification results.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: According to the collaborative functional blocks of the skid-mounted equipment, the functional collaboration and fault impact causal relationship analysis are carried out to build a causal association library; the causal association library is disassembled and clustered according to the input data, data analysis, and result output logic framework to obtain clustering results and corresponding relationship identifiers; based on the causal association library, the early warning path search is carried out to determine the graded early warning information; according to the relationship identifier and the graded early warning information, the collaborative functional blocks of the skid-mounted equipment are early warning monitored to obtain early warning identification results. The technical effect of realizing accurate monitoring and early warning of the operating status of the skid-mounted equipment and improving the operating safety, reliability and management efficiency of the skid-mounted equipment is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a process flow of a monitoring and early warning method for skid-mounted equipment provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a monitoring and early warning device for skid-mounted equipment provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: causal association library construction module 10, relationship identification acquisition module 20, graded warning information determination module 30, warning identification result acquisition module 40. DETAILED DESCRIPTION

[0012] The present application provides a monitoring and early warning method and device for skid-mounted equipment, which is used to solve the technical problem that it is difficult to fully and accurately grasp the cause and effect relationship of skid-mounted equipment in the prior art, resulting in inaccurate monitoring and early warning, low safety and reliability, and poor management efficiency.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a monitoring and early warning method for skid-mounted equipment, the method comprising: Step S100: Perform functional coordination and fault impact causal relationship analysis based on the coordinated functional blocks of the skid-mounted equipment, and build a causal association library.

[0015] Specifically, skid-mounted equipment is a combination of equipment that integrates multiple modules with specific functions. These modules are pre-manufactured, assembled and debugged in the factory, and then transported to the site as a whole for installation and use. For example, in the natural gas filling station scenario, the skid-mounted equipment includes natural gas storage modules, filling modules, metering modules, etc. In addition, in some emergency rescue scenarios, communication modules, lighting modules, etc. can be added according to actual needs so that rescue work can be carried out quickly in emergencies. First, the collaborative functional blocks of the skid-mounted equipment are analyzed to clarify their functional collaborative relationships. For example, in the oil extraction skid-mounted equipment, how do the oil extraction module, separation module, and storage module work together to achieve crude oil extraction, processing, and storage. At the same time, the connection relationship between the modules is sorted out to determine how they are related to each other (such as pipeline connection, circuit connection, etc.). Based on these module connection relationships, an adjacency matrix is ​​constructed to present the connection between modules. The type of connection (such as data transmission connection, power transmission connection, etc.) and weight (reflecting the importance or influence of the connection) of each module connection are accurately extracted to reasonably configure the connection attributes, and the connection weights are further calculated. Using these connection weights, the adjacency matrix is ​​converted into a weighted graph to obtain the connection association, in which the modules are nodes and the connection edge weights clearly represent the connection strength between the connection modules. The functional synergy relationship is evaluated for the success and abnormality of the synergy function. After the evaluation, the influencing factors are deeply analyzed and decomposed into a set of successful factors and a set of abnormal factors. The factor contribution is calculated with the help of the mean square error, and the initial causal graph is generated based on the factor contribution. Finally, the historical sample data is fully utilized, and the time series causal analysis method is used to carefully explore the correlation of the influence of each factor on the results of the synergistic function. The initial causal graph is optimized based on the correlation, so as to establish an accurate causal relationship. The constructed connection association and causal relationship are organically integrated to successfully build a causal association library. By analyzing the causal relationship between the functional coordination and fault impact of the skid-mounted equipment's collaborative functional blocks and building a causal association library, we have achieved a systematic sorting out and integration of the complex internal relationships of the skid-mounted equipment, effectively improving the accuracy and reliability of the skid-mounted equipment's operating status assessment and potential fault prediction.

[0016] Step S200: Decomposing and clustering the causal association library according to the input data, data analysis, and result output logic framework to obtain clustering results and corresponding relationship identifiers, wherein the relationship identifiers include input relationship identifiers, processing relationship identifiers, and output relationship identifiers.

[0017] Specifically, according to the logical framework of input data, data analysis, and result output, the causal relationship of each functional block in the causal association library is carefully decomposed. In this process, the causal relationship of input data-data processing-result output of each functional block is accurately determined. For example, for the monitoring data acquisition functional block, its input data is the original signal collected by the sensor, data processing is filtering, amplifying and other operations on the signal, and the result output is the effective monitoring data for analysis. Based on these clear causal relationships, an attribute matrix is ​​constructed to accurately record the relationship identification of each node (functional block) in the matrix, where the row represents the module and the column represents the relationship identification type (input, processing, output relationship identification). Then, according to the data source of the input data and data processing, a dependency graph is constructed. Through calculation, the degree of influence of the data source on the functional block is accurately evaluated, and the dependency influence weight is reasonably allocated. Next, according to the dependency influence weight of the data source on the functional block, a cross-weight matrix is ​​constructed to clearly identify the cross-influence relationship between the functional blocks. Finally, a clustering is carried out based on the attribute matrix to initially group together the functional blocks with similar relationship identifiers, and then a secondary clustering is carried out based on the cross-weight matrix to further optimize and subdivide the primary clustering results, thereby obtaining more accurate and meaningful clustering results and corresponding relationship identifiers. This has achieved the goal of further refining, classifying and structuring the complex causal association library, which helps to more clearly understand and grasp the data relationship and processing flow between the functional blocks of the skid-mounted equipment, providing strong support for subsequent efficient early warning path search and accurate monitoring and early warning, and significantly improving the pertinence and effectiveness of monitoring the operating status of skid-mounted equipment.

[0018] Step S300: According to the clustering results and the corresponding relationship identifiers, a warning path search is performed based on the causal association library to determine the graded warning information.

[0019] Specifically, the clustering results are standardized with the same data source to ensure that the data from the same data source is consistent in terms of format, unit, etc., which is convenient for subsequent unified analysis and processing. After the standardization is completed, the input data connection between the data source and the functional block is established so that the data can be accurately transmitted between the data source and the functional block. Then, taking the input end of the data source as the starting point, a comprehensive and in-depth path search is carried out based on the constructed causal association library. During the search process, the target warning functional blocks are determined. These target warning functional blocks may be single devices or functional units composed of multiple devices. According to the correlation between the search path and the path in the causal association library, the influence weight of the target warning functional block is calculated. For example, if a search path is highly correlated with a high-risk fault path in the causal association library, the corresponding target warning functional block will have a higher influence weight. Finally, based on the total amount of influence weights of the target warning functional blocks in the search path, the hierarchical warning information is determined. The functional blocks corresponding to the paths with higher total influence weights will be assigned higher warning levels, thereby realizing hierarchical warnings, so that operators can prioritize high-risk potential faults according to the warning levels. It can accurately locate the potential risk propagation path in the complex system of skid-mounted equipment, quantify the risk level based on the path correlation, and generate targeted and hierarchical graded warning information, which greatly improves the accuracy and effectiveness of the warning, enables operators to quickly identify high-risk areas and take priority measures, and effectively reduce the losses and impacts caused by equipment failures.

[0020] Step S400: Perform early warning monitoring of the collaborative functional blocks of the skid-mounted equipment according to the relationship identifier and the hierarchical early warning information to obtain an early warning identification result.

[0021] Specifically, according to the relationship identifier, the monitoring system of the collaborative functional blocks of the skid-mounted equipment is configured in a targeted manner. The input relationship identifier of each functional block is clarified to determine the data type and source to be collected. For example, for the functional block related to temperature, a temperature sensor is configured to collect real-time temperature data; according to the processing relationship identifier, the corresponding data processing module, such as data filtering, data conversion, etc., is set to ensure that the collected data can be processed according to the predetermined logic; according to the output relationship identifier, the output destination and format of the data are determined for subsequent early warning analysis. The monitoring system is started to collect data from each collaborative functional block in real time. The data collection frequency is set according to the equipment operation characteristics and early warning requirements. For example, for key parameters (such as pressure, flow, etc.), high-frequency collection (collection once per second or per millisecond) can be used, and for relatively minor parameters, the collection frequency can be appropriately reduced (collection once per minute or per hour). At the same time, a preliminary quality check is performed on the collected data to eliminate obviously abnormal data points (such as data beyond a reasonable range) to ensure the accuracy and reliability of the data. The real-time collected and processed data is compared with the graded early warning information. For each collaborative functional block, according to its corresponding graded early warning standard, it is determined whether the current data reaches or exceeds the corresponding early warning threshold. Consider the weight factors in the graded warning information and make a comprehensive judgment on the warnings affected by multiple factors. If the warning of a functional block is affected by multiple data sources or other functional blocks, the degree of influence of each factor is comprehensively evaluated according to the predetermined weight distribution. For example, the operating status of a device is affected by three factors: pressure, flow and temperature, and their weights are 0.3, 0.4 and 0.3 respectively. When the pressure data reaches the mild warning level, the flow data is normal, and the temperature data reaches the moderate warning level, the final warning level is determined by weighted calculation (such as calculating the comprehensive warning index = pressure warning index × 0.3 + flow warning index × 0.4 + temperature warning index × 0.3). Generate the warning identification result based on the comparison and judgment results. The warning identification result should contain detailed information, such as the time when the warning occurs, the collaborative functional blocks involved, the warning level, and the possible causes (based on the causal association library analysis). The warning identification results are fed back to the relevant personnel or systems in a timely manner through various means, such as popping up a striking warning information window on the display screen of the monitoring center to display the detailed warning content; at the same time, sending warning notifications to the operator's mobile terminal to ensure that the operator can obtain the warning information in the first time and ensure the safe and stable operation of the skid-mounted equipment.

[0022] In a possible implementation, step S100 further includes: Step S110: Obtaining the module connection relationship and functional coordination relationship of the skid-mounted equipment.

[0023] Step S120: Obtain connection association according to the module connection relationship.

[0024] Step S130: According to the functional synergy relationship, the synergy function success and abnormality evaluation is performed, and the causal relationship analysis is performed based on the influencing factors of the synergy function success and abnormality evaluation to establish a causal relationship.

[0025] Step S140: Merge the connection association with the causal relationship to construct the causal association library.

[0026] Specifically, for skid-mounted equipment, different functional equipment is integrated into one or more skid bodies through modular assembly, and the module connection relationship is comprehensively sorted out. This requires analysis of the physical structure and electrical connection of the skid-mounted equipment, and clarification of how the modules are connected through pipelines, lines, etc. For example, in an oil production skid-mounted equipment, the pipeline connection direction and connection interface type between the oil production module and the oil-water separation module, as well as the circuit connection layout between the electrical control module and each execution module are determined. At the same time, for the functional synergy relationship, during the operation of the skid-mounted equipment, a multi-type sensor network is deployed to monitor the operating parameters of each module (such as temperature, pressure, flow, voltage, current, etc.) in real time and accurately. The massive amount of operating data collected is transmitted to the data processing center, and the intrinsic correlation between the changes in the operating parameters of different modules is discovered through the association rule mining algorithm, so as to infer the functional synergy relationship; the cluster analysis algorithm is used to classify data points with similar functional synergy characteristics into one category, and the functional synergy mode is further clarified. At the same time, combined with the expert system, industry experience and knowledge are integrated into the analysis process, and the analysis results are verified and optimized to ensure that the acquired functional synergy relationship is accurate and reliable.

[0027] According to the actual situation of module connection, the adjacency matrix is ​​constructed to intuitively present the connection status between modules in the form of a matrix. During the construction process, the type (such as hydraulic connection, signal connection, etc.) and weight (reflecting the importance of the connection to the overall operation of the equipment) of each module connection are extracted, and the connection properties are reasonably configured accordingly. Then, the connection weights are accurately calculated according to the connection properties, and the various characteristics of the connection are quantified. Finally, with these connection weights, the adjacency matrix is ​​converted into a weighted graph. In the weighted graph, each module becomes a node, and the weight of the connection edge clearly indicates the connection strength between the connected modules. In this way, the originally complex module connection relationship is converted into a connection association model that is easy to analyze and process.

[0028] According to the clear functional synergy relationship, the success and abnormality evaluation of the synergy function is carried out. By collecting a large amount of actual operation data, the operation results of the synergy function are evaluated using data analysis algorithms to determine whether it has successfully achieved the expected function and whether there are any abnormalities. For example, for the water purification synergy function of the sewage treatment skid-mounted equipment, the success is evaluated by monitoring whether the water quality indicators after treatment meet the standards. If the water quality fluctuates abnormally, it is considered to be abnormal. After the evaluation, the various factors affecting the success and abnormality of the synergy function are deeply analyzed and decomposed into a success factor set and an abnormal factor set. Then, based on these factor sets, the contribution of each factor is quantified using the mean square error calculation method, so as to generate an initial causal diagram and preliminarily show the relationship between the factors and the synergy function results. Subsequently, the historical sample data is fully utilized, and with the help of time series causal analysis technology, the influence correlation of each factor on the synergy function results is deeply explored, and the causal relationship between the factors is further clarified. Finally, the initial causal diagram is optimized based on the mined influence correlation, unreasonable causal relationships are removed, and the missing key relationships are supplemented, so as to establish an accurate and reliable causal relationship model.

[0029] When the connection association and causal relationship are integrated to build a causal association library, a special causal association library storage structure is first created using the database management system. The structure has the ability to store module connection information, causal relationship logic, and the mapping of the association between the two. Then, the module nodes in the connection association are mapped one-to-one with the factors in the causal relationship through the data mapping algorithm to ensure the accurate association between physical connection and functional impact. For the connection attributes (such as connection type, weight, etc.) in the connection association and the contribution of the influencing factors in the causal relationship, the data fusion algorithm is used to calculate and generate the fused association weight to quantify the degree of mutual influence between the two after fusion. In the fusion process, the data verification mechanism is used to verify the fusion results based on historical operation data and actual fault cases to ensure that the fused causal association conforms to the actual operation logic of the equipment. Finally, the complete fused information is entered into the causal association library according to the predetermined data format and storage rules to establish a comprehensive, accurate and interrelated database containing module connection relationships and causal relationships. It achieves an in-depth analysis of the internal structure and functional collaboration of skid-mounted equipment, transforms the complex module connection relationship and functional coordination relationship into a causal association library, and provides a comprehensive, accurate and structured data foundation and logical basis for skid-mounted equipment fault diagnosis, performance optimization and precise monitoring and early warning, effectively improving the intelligence level and reliability of skid-mounted equipment operation management.

[0030] In a possible implementation, step S120 further includes: Step S121: construct an adjacency matrix according to the module connection relationship.

[0031] Step S122: extract the type and weight of each module connection and configure the connection attributes.

[0032] Step S123: configuring the connection weight according to the connection attribute.

[0033] Step S124: converting the adjacency matrix into a weighted graph based on the connection weights to obtain the connection associations, wherein the modules are nodes and the connection edge weights represent the connection strengths between the connection modules.

[0034] Specifically, when constructing an adjacency matrix based on the module connection relationship of the skid-mounted equipment, it is first necessary to number all the modules in the skid-mounted equipment to uniquely identify each module. For example, for a skid-mounted equipment containing an oil production module, a separation module, a storage module, etc., they can be numbered 1, 2, 3, etc. Then, create a two-dimensional matrix with the number of rows and columns equal to the total number of modules. For the elements in the matrix, if there is a connection relationship between module i and module j, the positions in the i-th row and j-th column of the matrix and the j-th row and i-th column (because the connection relationship is bidirectional) are marked as 1, indicating that there is a connection; if there is no connection, it is marked as 0. In this way, an adjacency matrix that can intuitively reflect the module connection status is constructed, through which it is possible to quickly determine whether there is a direct connection between any two modules.

[0035] After the adjacency matrix is ​​constructed, the type and weight of each module connection are extracted to configure the connection attributes. Through field surveys and consulting equipment technical documents, the types of module connections are determined, such as hydraulic connections, electrical connections, data transmission connections, and other different types in skid-mounted equipment. For the determination of connection weights, multiple factors need to be considered comprehensively, such as the importance of the connection, the frequency of data or energy transmission, and the degree of influence of the connection on the overall function of the equipment. For example, for the pipeline connection between the oil production module and the separation module (which belongs to the hydraulic connection type), if the pipeline is responsible for transmitting a large amount of crude oil and is crucial to the subsequent separation process, then it is given a higher weight value, such as 0.8; and for the electrical connection between some auxiliary equipment, if it is only used to transmit control signals and has little impact on the overall function, it is given a relatively low weight value, such as 0.3. According to these extracted and calculated connection types and weights, the corresponding attribute information is configured for each connection relationship, so that the characteristics of the connection can be described more accurately later.

[0036] The connection weight is determined according to the configured connection attributes. Different calculation methods are used to quantify the connection weight for different types of connection attributes. For numerical connection attributes (such as connection bandwidth, pipe diameter, etc.), they are directly used as part of the connection weight; for classification attributes (such as connection type is hydraulic, electrical, etc.), they are converted into corresponding numerical weights through a pre-set weight mapping table. For example, the weight mapping value of the hydraulic connection is set to 0.6, the weight mapping value of the electrical connection is set to 0.4, and so on. At the same time, it is also necessary to consider the impact of factors such as the stability and reliability of the connection on the weight, and adjust the weight by introducing a correction coefficient. For example, if a connection has poor stability and is prone to failure, a correction coefficient less than 1 (such as 0.8) is multiplied when calculating the weight to reduce its weight. After comprehensive calculation, an accurate connection weight is configured for each module connection to more accurately reflect the actual influence of the connection.

[0037] Based on the calculated connection weights, the adjacency matrix is ​​converted into a weighted graph to obtain the connection association. In the weighted graph, each module is a node, and the node number corresponds to the module number in the previous adjacency matrix. The connection edges between modules are represented by weighted line segments, and the weight of the connection edge is the previously configured connection weight, which clearly shows the connection strength between the connected modules. In this way, the module connection relationship originally represented in the form of a matrix is ​​converted into a connection association in the form of a weighted graph that is more intuitive and can better reflect the difference in connection strength. In the weighted graph, the degree of connection between each module can be intuitively observed. For example, a connection edge with a larger weight indicates that the corresponding two modules are closely connected, and data or energy transmission is frequent and important; while a connection edge with a smaller weight indicates that the connection is relatively weak. This connection association provides an important basis for further analysis of the overall structure and functional relationship of the skid-mounted equipment. It realizes the transformation of the abstract module connection relationship of the skid-mounted equipment into an intuitive and quantified connection association model. Based on the adjacency matrix, it integrates the connection type, weight and other attribute information to generate a weighted graph, which clearly presents the difference in connection strength between modules. It provides a structured, digital and more expressive data foundation and analysis perspective for the subsequent precise analysis of equipment structure, functional relationship and fault impact, and improves the accuracy and effectiveness of the understanding and processing of the internal connection logic of the skid-mounted equipment.

[0038] In a possible implementation, step S130 further includes: Step S131: Decomposing influencing factors according to the evaluation results of the success and abnormality of the collaborative function to obtain a success factor set and an abnormal factor set.

[0039] Step S132: Calculate factor contribution by using mean square error based on the success factor set and the abnormal factor set.

[0040] Step S133: Generate an initial causal diagram based on the factor contributions.

[0041] Step S134: Based on the historical sample data, through time series causal analysis, the influence correlation of each factor on the synergistic function results is explored.

[0042] Step S135: Optimize the initial cause-effect graph according to the impact correlation to obtain the cause-effect relationship.

[0043] Specifically, the data acquisition system is used to comprehensively collect various types of data during the operation of the skid-mounted equipment, including equipment operating status parameters (such as temperature, pressure, flow, speed, etc.), environmental monitoring data (such as ambient temperature, humidity, air pressure, etc.) and operation record data (such as valve opening changes, equipment start and stop time, etc.). Then, the principal component analysis (PCA) algorithm is used to reduce the dimension of these data, extract the main data features, and reduce data redundancy. Next, the reduced-dimensional data is input into a pre-trained classification model, which is built based on a large amount of historical data and expert experience, and can accurately judge the degree of correlation between the data and the success or abnormality of the collaborative function based on the data features. Through the classification results of the model, the data features that are highly correlated with the success of the collaborative function are screened out as success factors to form a success factor set; the data features that are closely related to the abnormality of the collaborative function are screened out as abnormal factors to form an abnormal factor set. At the same time, the factors initially screened out are manually reviewed and adjusted to ensure the accuracy and completeness of the factor set.

[0044] For each success factor X in the success factor set, i , construct a univariate linear model To predict the success score S, β0 and β1 are model parameters obtained by fitting the data using methods such as the least squares method. Calculate the mean squared error (MSE) of the predictions, where N is the number of samples, is the actual success score, is the success score predicted by the model. Finally, according to the formula contribution (X i ) = 1-MES i Calculate the success factor X i The factor contribution value of is. For the abnormal factor set, a similar approach is used. Use a univariate model to predict the abnormality score A, the contribution ,in is the actual abnormality score, is the predicted abnormality score. After obtaining the contribution values ​​of the success factor and the abnormal factor, normalization is performed. Normalize the contribution value to fall between 0 and 1, where is the total number of factors. This ensures that the contribution values ​​of different factors are comparable, which facilitates subsequent analysis and processing. For example, when generating a causal diagram or evaluating the importance of factors, it can more accurately reflect the relative contribution of each factor.

[0045] Each factor in the success factor set and the abnormal factor set is taken as a node and laid out in the graph according to its category (success factor or abnormal factor). Then, the weight and direction of the connection edge between nodes are determined according to the calculated factor contribution value. For factors with large factor contribution values, they are taken as the main causal starting point or key node, and directed connection edges are established with other factors that may be affected by them. The weight of the connection edge can be directly quantified by the size of the factor contribution value. The larger the contribution value, the higher the weight of the connection edge, indicating that the factor has a stronger influence on other factors. For example, if a success factor has a high contribution value, and it is judged to have a positive impact on several other factors based on domain knowledge and experience, then a directed edge is drawn from the factor node to other related factor nodes, and the corresponding weight is marked. In this way, all factors and their interrelationships are presented in a graphical way to form an initial causal graph, which preliminarily shows the possible causal relationship and influence between the factors, and provides a basic framework for subsequent causal relationship optimization and analysis.

[0046] With the help of historical sample data, the time series causal analysis method is used to deeply explore the correlation of the impact of each factor on the synergistic function results. Collect historical data during the long-term operation of the skid-mounted equipment, which contains the values ​​of each factor at different time points and the corresponding synergistic function results. For example, for chemical production skid-mounted equipment, collect historical data on factors such as reaction temperature, raw material flow, catalyst activity, and final product quality data in the past few months or even years. Then, through the time series analysis algorithm, analyze the order and correlation between the changes in each factor in the time dimension and the changes in the synergistic function results. Determine which factor changes will have a significant impact on the synergistic function results after a certain time lag, as well as the direction (positive correlation or negative correlation) and intensity of this impact, so as to obtain the correlation information of the impact of each factor or factor combination on the synergistic function results.

[0047] The initial causal diagram is optimized based on the mined impact correlation, and the causal relationship in the initial causal diagram is corrected and improved based on the impact correlation analysis results. If it is found that there is no connection between two factors in the initial causal diagram, but it is determined through the impact correlation analysis that there is a significant causal relationship between them, then the corresponding directed line segment is added to the causal diagram; if it is found that the causal relationship between a factor and the synergistic function result in the initial causal diagram is in the wrong direction, it is corrected; at the same time, for the causal relationship with weak correlation, the thickness or weight of the connecting line segment is appropriately adjusted to more accurately reflect the actual situation. After such an optimization process, unreasonable causal relationships are removed, and missing key relationships are supplemented, and finally a model that can accurately reflect the true causal relationship of each factor in the synergistic function of the skid-mounted equipment is obtained. It is realized to decompose the influencing factors from the synergistic function evaluation results, quantify their contributions, construct and optimize the causal diagram, so as to accurately mine the causal relationship between each factor and the synergistic function result, and provide reliable technical support for equipment operation analysis, fault diagnosis and performance optimization.

[0048] In a possible implementation, step S134 further includes: Step S1341: setting a dynamic time window and a factor variable screening gradient, wherein the dynamic time window is used to perform an impact correlation analysis of multiple time lengths, and the factor variable screening gradient is used to control the continuous increase in the number of factors.

[0049] Step S1342: Variables are set according to the dynamic time window and factor variable screening gradient, and the dependency of each factor on the synergistic function result is identified through the time series analysis network model to obtain the influence correlation of each factor or factor combination on the synergistic function result.

[0050] Specifically, first, determine the range of the time window. For example, for the collaborative function data of a certain device, set the shortest time window to 1 day and the longest time window to 30 days. Then, set the dynamic time window with a certain step size (such as 1 day). Starting from the shortest time window, increase the step size in sequence to form a series of time windows of different lengths, such as 1 day, 2 days, 3 days, etc., until the longest time window is 30 days. In this way, the same set of data can be analyzed for impact correlation at different time lengths to fully capture the short-term, medium-term and long-term impact effects. For example, when analyzing the impact of the equipment temperature factor on the collaborative function, through time windows of different lengths, it is observed that the immediate impact of temperature fluctuations within a day on the collaborative function, as well as the long-term impact of temperature change trends within a month on the collaborative function. For the factor variable screening gradient, first determine all factors that may affect the collaborative function. Assume that there are 10 factors in total, such as equipment operating parameters (pressure, flow, speed, etc.), environmental factors (temperature, humidity, etc.) and operating factors (operating frequency, operating duration, etc.). Then, starting from a single factor, increase the number of factors in sequence to form a gradient. First, analyze the impact of a single factor (such as pressure) on the synergistic function, then analyze the impact of a combination of two factors (such as pressure and flow), then analyze the impact of a combination of three factors (such as pressure, flow, and speed), and so on, until all 10 factor combinations are included. In this way, we can gradually and deeply explore the impact of different numbers of factor combinations on the results of synergistic functions, from simple single-factor analysis to complex multi-factor interaction analysis, and comprehensively explore the relationship between each factor and the synergistic function, providing a rich and detailed data foundation and analysis dimension for subsequent correlation analysis and causal diagram construction.

[0051] The variables are set precisely according to the set dynamic time window and factor variable screening gradient. The dynamic time window changes from short to long, such as from hours to weeks. After each adjustment of the window length, the factor variable screening gradient is combined to divide the data of different number of factor combinations according to the time window. The long short-term memory network (LSTM) time series analysis network model is used to input these processed data into the model. LSTM has a special memory unit structure that can well capture the long-term dependencies in the time series. When processing multivariate time series data, the model will simultaneously consider the changes of multiple factor variables at different time points, and through repeated learning and training of the input data, the interaction pattern between the factors is excavated. For example, when analyzing the synergistic function of chemical production skid-mounted equipment, the input factor variables include reaction temperature, raw material flow, catalyst concentration, etc. As the time window changes and the factor combination is different, the LSTM model learns the change rules of these variables over time and identifies the dependency between each factor or factor combination and the synergistic function results (such as product quality, production efficiency, etc.). Finally, the model outputs the correlation of the impact of each factor or factor combination on the synergistic function results, thus clearly revealing which factors or factor combinations have the most significant impact on the synergistic function at different time scales, providing a key basis for subsequent causal relationship analysis and optimization. It has achieved comprehensive and accurate mining of the dependency and impact correlation between each factor or factor combination and the synergistic function results at multiple time scales and multiple factor combination dimensions.

[0052] In a possible implementation, step S200 further includes: Step S210: Decompose the causal relationship of each functional block according to the input data, data analysis, and result output logic framework to determine the causal relationship of input data-data processing-result output of each functional block.

[0053] Step S220: Based on the causal relationship of input data-data processing-result output of each functional block, an attribute matrix is ​​constructed to record the relationship identification of each node, where the row represents the module and the column represents the relationship identification type.

[0054] Step S230: construct a dependency graph based on the input data and the data source of the data processing, calculate the influence of the data source on the functional block, and assign dependency influence weights.

[0055] Step S240: constructing a cross-weight matrix according to the dependency influence weights of the data source on the functional block, so as to identify the cross-influence relationship.

[0056] Step S250: Perform a primary clustering based on the attribute matrix, and perform a secondary clustering based on the cross weight matrix to obtain the clustering result.

[0057] Specifically, the input and output data of each functional block of the skid-mounted equipment are comprehensively collected, including sensor data, operating instructions, and equipment status, and pre-processed to ensure data availability. Then, the Granger causality test algorithm is used to analyze the causality of input and output data, a Bayesian network model is constructed to describe the causal relationship of data processing, and a decision tree algorithm is used to analyze the logic of the processing flow. Then, the cross-validation method is used to evaluate the accuracy of the mined causal relationship, and the model is optimized based on the verification results. By adjusting the Granger causality test lag order, improving the Bayesian network conditional probability table, or improving the decision tree branching rules, the causal relationship between input data, data processing, and result output of each functional block is finally accurately determined.

[0058] The feature engineering algorithm is used to process the information of each functional block, and the key features are extracted as the column identification type of the attribute matrix. The principal component analysis (PCA) algorithm is used to screen out the input data types, key steps of data processing, and key features of the result output that are important and representative of the functional blocks. The number of rows of the attribute matrix is ​​determined according to the number of functional blocks, and each functional block is scanned one by one. For each functional block, the corresponding input data source and type are filled in the corresponding column according to the predefined coding system (for example, unique digital codes are assigned to different types of input data). The name of the algorithm used (the function name in the algorithm library or the unique identifier of the custom algorithm) or the description of the processing flow is recorded in detail in the data processing column, and the format of the output data, the flow destination, and other information are filled in the result output column, so as to construct the attribute matrix and accurately record the relationship identification of each node.

[0059] With data sources (such as sensors, external data interfaces, etc.) and functional blocks as nodes, a dependency graph is constructed. For each functional block, determine the data source it directly depends on, and draw a directed edge from the data source node to the functional block node in the dependency graph. For example, in a chemical reaction skid-mounted device, the temperature sensor data source node points to the reactor temperature control functional block node, indicating that the reactor temperature control depends on the data of the temperature sensor. Considering the data transfer and interaction between functional blocks, if the output of one functional block is used as the input of another functional block, the corresponding directed edge is drawn. For example, if the product output of the reactor is used as the input of the subsequent separation and purification functional block, a directed edge is drawn between the reactor node and the separation and purification node, with the direction from the reactor to the separation and purification. Use a graph database (such as Neo4j) or data structures such as an adjacency matrix to store the dependency graph to facilitate subsequent query, modification, and analysis operations. In a graph database, attributes can be added to nodes and edges, such as the type of data source, the functional description of the functional block, etc., to enrich the information of the dependency graph. The index system is constructed by comprehensively considering multiple factors of the data source, including data accuracy (error rate compared with the standard value or reliable data source), stability (calculation of variance or standard deviation), real-time (update frequency or delay time), reliability (based on historical failure or maintenance records) and importance to functional blocks (data analysis). The judgment matrix is ​​constructed using the analytic hierarchy process (AHP) to determine the weight of each indicator, assuming that the weight of data accuracy is 0.3, stability is 0.2, real-time is 0.2, reliability is 0.1, and importance is 0.2. Taking the temperature sensor data source as an example, its accuracy score is 0.98, the standard deviation is 0.5, that is, the stability score is 0.8, the real-time score is 0.9, the reliability score is 0.95, and the importance score for reactor temperature control is 0.9. The impact score = 0.3×0.98+0.2×0.8+0.2×0.9+0.1×0.95+0.2×0.9=0.899. The calculated impact score is normalized so that the sum of the impact weights of all data sources on a specific functional block is 1. The normalized weights are assigned to the corresponding edges in the dependency graph, that is, the edges from the data source node to the functional block node. In this way, each edge in the dependency graph carries a weight, indicating the degree of dependency influence of the data source on the functional block.

[0060] The number of rows and columns of the cross-weight matrix are equal to the number of functional blocks plus the number of data sources. For example, if there are 5 functional blocks and 3 data sources, the cross-weight matrix is ​​an 8×8 square matrix. The elements in the matrix are classified and defined. The elements on the main diagonal are used to represent the importance or stability weight of the data source or the functional block itself (initialized to 1 or determined by other methods). The elements on the non-main diagonal are used to represent the cross-influence weight between the data source and the functional block or between the functional blocks, and are filled according to the weights in the dependency graph. For the cross-influence weight between the data source and the functional block, the weight on the corresponding edge in the dependency graph is directly filled into the corresponding position in the cross-weight matrix. For example, if the dependency influence weight of the temperature sensor data source on the reactor temperature control functional block in the dependency graph is 0.397, then 0.397 is filled at the intersection of the row corresponding to the temperature sensor data source and the column corresponding to the reactor temperature control functional block in the cross-weight matrix. For the cross-influence weight between functional blocks, it is determined by analyzing the data transfer relationship and the degree of dependence between functional blocks. If there is data dependency between two functional blocks and there is a corresponding directed edge connection in the dependency graph, the cross-influence weight is determined according to the edge weight and the importance of data transfer. For example, there is data transfer between the reactor and the separation and purification functional blocks, and according to the dependency graph and the actual situation, the reactor has a greater impact on separation and purification, with a weight of 0.6. In the cross-weight matrix, fill 0.6 at the intersection of the row corresponding to the reactor functional block and the column corresponding to the separation and purification functional block. At the same time, fill a symmetrical value (such as 0.4, determined according to the specific situation) at the intersection of the row corresponding to the separation and purification functional block and the column corresponding to the reactor functional block to indicate the cross-influence relationship between them. Check and adjust the constructed cross-weight matrix to ensure the symmetry (if there is a symmetric relationship) and consistency of the matrix. For example, check the logical rationality of the cross-influence weights between functional blocks. If it is found that the influence weight of a functional block on another functional block does not match the actual situation, re-analyze the data transfer relationship and the degree of dependence and correct the weight. The cross-weight matrix is ​​verified by simulation data or actual case data to observe whether the weights in the matrix can accurately reflect the cross-influence relationship between data sources and functional blocks and between functional blocks. For example, the data value of a data source is changed, and the impact on the relevant functional blocks is calculated based on the weights in the matrix, and compared with the changes in the actual equipment operation. If there is a large deviation, the weights in the matrix are further optimized.

[0061] Based on the primary clustering of the attribute matrix, the K-means or hierarchical clustering method is used to cluster the attribute matrix. First, the eigenvectors of each module are extracted from the attribute matrix. These eigenvectors reflect the attributes of the module in terms of input data type, data processing method, and result output form. Then, the eigenvectors are divided into different clusters using the K-means algorithm, or a clustering tree is constructed using hierarchical clustering. The clustering results are obtained by cutting the clustering tree to identify modules with similar functions. Based on the secondary clustering of the cross-weight matrix, the spectral clustering method is used to cluster the cross-relationship matrix. The cross-influence relationship information between modules is obtained from the cross-weight matrix. By constructing a graph structure (regarding modules as nodes and cross-influences as edges), the spectral clustering algorithm is used to segment the graph to identify modules or variables with strong cross-influences. The results of attribute matrix clustering and cross-weight matrix clustering are fused, and a joint clustering model is constructed. , where α and β are weight parameters. Adjust the values ​​of α and β according to actual needs and data characteristics, comprehensively consider the contribution of attribute matrix and cross-relation matrix in clustering, and obtain the final clustering result.

[0062] In a possible implementation, step S300 further includes: Step S310: performing standardization processing on the same data source according to the clustering result, and establishing an input data connection between the data source and the functional block.

[0063] Step S320: Based on the clustering results, taking the input end of the data source as the starting point, performing a path search according to the causal association library, determining the target early warning functional block, and obtaining the influence weight of the target early warning functional block according to the correlation between the search path and the path in the causal association library. The target early warning functional block includes a single device or a combination of devices.

[0064] Step S330: Determine the graded warning information based on the total amount of impact weights of the target warning function block in the search path.

[0065] Specifically, the data in the clustering results are standardized with the same data source. For example, for data such as pump flow, compressor inlet pressure, and heat exchanger temperature difference, they are all normalized to the interval [0, 1] to eliminate the differences between different devices due to the inconsistency of ports, protocols, and units, which is convenient for subsequent early warning analysis. After the standardization is completed, according to the functional logic and data flow of the equipment, the input data connection between the data source and the functional block is established to ensure that the data can be accurately transmitted to the corresponding functional block for processing and analysis.

[0066] The input end of the data source is determined based on the clustering results. For example, in the existing standardized processing, the device port corresponding to the data such as pump flow, compressor inlet pressure, and heat exchanger temperature difference is the data source input end. Taking these data source input ends as the starting point, the path search is carried out according to the causal association library. The causal association library records in detail the causal association information between devices and between the functional blocks inside the equipment. For example, the path is pump, compressor, heat exchanger, and desulfurization tower. Starting from the pump data source input end, use a suitable path search algorithm (such as depth-first search or breadth-first search) to search in the causal association library. Assuming that the depth-first search is adopted, firstly, the connection relationship between the pump and the compressor is deeply explored, and it is found that the operating state of the pump will directly affect the operation of the compressor, so the path segment "pump to compressor" is determined. Then, continue to explore from the compressor to find its causal relationship with the heat exchanger, and further expand the path to "pump to compressor to heat exchanger". By analogy, the complete path "pump to compressor to heat exchanger to desulfurization tower" is finally obtained. In this process, the nodes and path information passed through each step are recorded in detail. These records will provide a key basis for the subsequent determination of the target early warning functional blocks and the calculation of the impact weights. According to the searched path, the pumps, compressors, heat exchangers, and desulfurization towers are all target early warning functional blocks. They each have important functions and are interconnected through data and operation logic. For example, changes in the flow rate of the pump will affect the inlet pressure of the compressor, which in turn affects the heat exchange effect of the heat exchanger, and ultimately affects the desulfurization efficiency of the desulfurization tower. Therefore, these devices are in a critical position during the operation of the entire skid-mounted equipment. Once a problem occurs in a certain link, it may trigger a chain reaction and affect the normal operation of the entire system. Therefore, they are identified as target early warning functional blocks. In order to obtain the impact weights of the target early warning functional blocks, a dynamic weight matrix W is constructed. dyn , this matrix is ​​constructed based on the strength of the causal relationship between the equipment in the system. The construction process is as follows: Determine the number of rows and columns of the matrix: For example, since there are four types of equipment in the system, namely pumps, compressors, heat exchangers, and desulfurization towers, the matrix is ​​a 4×4 square matrix. The strength of the causal relationship between the equipment is analyzed from the causal association library to determine the weight value. For example, from pumps to compressors, based on the understanding of equipment operation and the analysis of historical data, it is found that the operating status of the pump has an important impact on the operation of the compressor. After quantitative evaluation (possibly through data correlation analysis, expert experience judgment, etc.), its weight is determined to be 0.8, so 0.8 is filled in the first row and second column of the matrix to represent the weight of the pump's impact on the compressor. Similarly, the weight of the compressor to the heat exchanger is 0.6, and 0.6 is filled in the second row and third column of the matrix; the weight of the heat exchanger to the desulfurization tower is 0.9, and 0.9 is filled in the third row and fourth column of the matrix. For other elements in the matrix that do not have a direct causal relationship, fill in 0 according to the actual situation (indicating that there is no direct impact). In this way, a dynamic weight matrix is ​​obtained. In this matrix, the value of the element represents the weight relationship between adjacent nodes. The weight from the pump to the compressor is 0.8, which means that the weight of the pump on the compressor is 0.8; the weight from the compressor to the heat exchanger is 0.6, which means that the weight of the compressor on the heat exchanger is 0.6; the weight from the heat exchanger to the desulfurization tower is 0.9, which means that the weight of the heat exchanger on the desulfurization tower is 0.9. In the dynamic weight matrix W dyn The corresponding weight relationship in the causal chain can accurately determine the impact weight of each target warning functional block in the entire causal chain. These weights will provide key quantitative basis for graded warning in subsequent steps, and help to more accurately evaluate the importance and degree of impact of different equipment or equipment combinations in the system, thereby providing strong support for the effective operation of the early warning system.

[0067] Calculate the total impact weight of the target warning function block in the search path, according to the dynamic weight matrix W dyn , the weight from the pump to the compressor is 0.8, the weight from the compressor to the heat exchanger is 0.6, and the weight from the heat exchanger to the desulfurization tower is 0.9, so the total weight P weight=0.8+0.6+0.9=2.3, then, the graded warning information is determined based on the calculated total amount of impact weights. According to the pre-set classification rules, when the total amount of weights reaches or exceeds a certain threshold (for example, the warning level may be set to be severe when the total amount of weights is greater than or equal to 2), the warning level is determined to be severe. If the data source only affects a single module, then the corresponding level of warning information is issued for the single device to remind the operator of the possible risks of the device and the measures to be taken. For example, if a data source only affects the pump, and the warning level corresponding to the calculated total amount of weights is intermediate, then an intermediate warning for the pump is issued to remind the operator to pay attention to the operating status of the pump, and it may be necessary to check the relevant parameters and maintenance of the pump. When the data source has an impact on multiple devices, the impact on each device is analyzed in detail according to the access and calculation path of the data source. For example, in the above path, the pump, compressor, heat exchanger, and desulfurization tower are all affected. According to the weights involved in the path and the importance of the equipment itself, the warning levels of different devices are determined respectively. For equipment with high importance and large impact weights, such as desulfurization towers (which are affected by the previous equipment with a high sum of impact weights), a higher level of warning is given; for relatively minor equipment with small impact weights, such as compressors (only affected by pumps, with a weight of 0.8), a relatively low level of warning is given, but operators still need to pay attention to it in order to discover potential problems in time, take effective prevention and treatment measures, and ensure the safe and stable operation of the entire system. Through this hierarchical warning method based on the total amount of impact weights, operators can be more accurately informed of the risk status of different equipment or equipment combinations in the system, improve the effectiveness and pertinence of warnings, and provide strong support for timely response measures.

[0068] Embodiment 2, based on the same inventive concept as the monitoring and early warning method for skid-mounted equipment in the above embodiment, Figure 2 As shown, the present application provides a monitoring and early warning device for skid-mounted equipment, and the device and method embodiments in the present application are based on the same inventive concept. The device includes: The causal association library construction module 10 is used to perform functional coordination and fault impact causal relationship analysis based on the coordinated functional blocks of the skid-mounted equipment, and to construct a causal association library.

[0069] The relationship identifier acquisition module 20 is used to disassemble and cluster the causal association library according to the input data, data analysis, and result output logic framework to obtain clustering results and corresponding relationship identifiers, and the relationship identifiers include input relationship identifiers, processing relationship identifiers, and output relationship identifiers.

[0070] The graded warning information determination module 30 is used to perform a warning path search based on the causal association library according to the clustering results and the corresponding relationship identifiers, and determine the graded warning information.

[0071] The early warning identification result acquisition module 40 is used to perform early warning monitoring of the collaborative functional blocks of the skid-mounted equipment according to the relationship identifier and the hierarchical early warning information to obtain an early warning identification result.

[0072] Furthermore, the causal association library construction module 10 also includes: The connection relationship acquisition unit is used to obtain the module connection relationship and functional coordination relationship of the skid-mounted equipment.

[0073] The connection association obtaining unit is used to obtain the connection association according to the module connection relationship.

[0074] The causal relationship establishing unit is used to evaluate the success and abnormality of the collaborative function according to the functional collaborative relationship, and to perform causal relationship analysis based on the influencing factors of the collaborative function success and abnormality evaluation to establish a causal relationship.

[0075] The causal relationship fusion unit is used to fuse the connection association with the causal relationship to construct the causal relationship library.

[0076] Furthermore, the connection association acquisition unit further includes: The adjacency matrix construction unit is used to construct an adjacency matrix according to the module connection relationship.

[0077] The connection attribute configuration unit is used to extract the type and weight of each module connection and configure the connection attributes.

[0078] A connection weight configuration unit is used to configure the connection weight according to the connection attribute.

[0079] A weighted graph conversion unit is used to convert the adjacency matrix into a weighted graph based on the connection weights to obtain the connection associations, wherein the modules are nodes and the connection edge weights represent the connection strengths between the connection modules.

[0080] Furthermore, the causal relationship establishing unit also includes: The factor set acquisition unit is used to decompose the influencing factors according to the evaluation results of the success and abnormality of the collaborative function to obtain the success factor set and the abnormal factor set.

[0081] The factor contribution calculation unit is used to calculate the factor contribution through mean square error based on the success factor set and the abnormal factor set.

[0082] The initial causal graph generating unit is used to generate an initial causal graph according to the factor contribution.

[0083] The impact correlation mining unit is used to mine the impact correlation of each factor on the collaborative function results through time series causal analysis based on historical sample data.

[0084] An initial cause-effect graph optimization unit is used to optimize the initial cause-effect graph according to the impact correlation to obtain the cause-effect relationship.

[0085] Furthermore, the impact correlation mining unit includes: The factor variable screening gradient setting unit is used to set a dynamic time window and a factor variable screening gradient. The dynamic time window is used to perform influence correlation analysis of multiple time lengths, and the factor variable screening gradient is used to control the continuous increase in the number of factors.

[0086] The dependency identification unit is used to set variables according to the dynamic time window and factor variable screening gradient, identify the dependency of each factor on the synergistic function result through the time series analysis network model, and obtain the influence correlation of each factor or factor combination on the synergistic function result.

[0087] Furthermore, the relationship identification acquisition module 20 includes: The causal relationship determination unit is used to perform causal relationship decomposition on each functional block according to the input data, data analysis, and result output logic framework, and determine the causal relationship of input data-data processing-result output of each functional block.

[0088] The relationship identification recording unit is used to construct an attribute matrix based on the causal relationship of input data-data processing-result output of each functional block, and record the relationship identification of each node, where the row represents the module and the column represents the relationship identification type.

[0089] The dependency impact weight allocation unit is used to construct a dependency graph based on the input data and the data source of the data processing, calculate the degree of influence of the data source on the functional block, and allocate the dependency impact weight.

[0090] The cross-weight matrix construction unit is used to construct a cross-weight matrix according to the dependency influence weight of the data source on the functional block, so as to identify the cross-influence relationship.

[0091] The secondary clustering unit is used to perform primary clustering based on the attribute matrix and perform secondary clustering according to the cross weight matrix to obtain the clustering result.

[0092] Furthermore, the graded warning information determination module 30 includes: The input data connection establishing unit is used to perform standardization processing on the same data source according to the clustering result, and establish an input data connection between the data source and the functional block.

[0093] An influence weight acquisition unit is used to perform a path search based on the clustering result and the input end of the data source as a starting point according to the causal association library to determine the target early warning functional block, and obtain the influence weight of the target early warning functional block according to the correlation between the search path and the path in the causal association library, wherein the target early warning functional block includes a single device or a combination of devices.

[0094] The hierarchical warning information determining unit is used to determine the hierarchical warning information based on the total amount of influence weights of the target warning function block in the search path.

[0095] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0097] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A monitoring and early warning method for skid-mounted equipment, characterized in that: include: Conduct functional coordination and fault impact causal relationship analysis based on the collaborative functional blocks of skid-mounted equipment, and build a causal association library; According to the input data, data analysis, and result output logic framework, the causal association library is disassembled and clustered to obtain clustering results and corresponding relationship identifiers, wherein the relationship identifiers include input relationship identifiers, processing relationship identifiers, and output relationship identifiers, wherein the clustering process includes: clustering the attributes of functional similarity according to the causal relationship of the functional blocks, clustering the cross-influence relationships according to the data source dependency based on the attribute clustering results, identifying the cross-influence strength of the causal relationship, obtaining clustering results, and generating relationship identifiers of causal relationship nodes according to the clustering results; According to the clustering results and the corresponding relationship identifiers, a warning path search is performed based on the causal association library to determine the graded warning information; Perform early warning monitoring of the collaborative functional blocks of the skid-mounted equipment according to the relationship identifier and the hierarchical early warning information to obtain an early warning identification result; Build a causal association library, including: Obtaining the module connection relationship and the functional coordination relationship of the skid-mounted equipment, wherein the functional coordination relationship is the relationship between the modules that need to cooperate with each other to realize the equipment function during the operation of the skid-mounted equipment, and the module connection relationship is the physical connection relationship between the modules; According to the module connection relationship, a connection association is obtained; According to the functional synergy relationship, the success and abnormality of the synergy function are evaluated, and the causal relationship analysis is performed based on the influencing factors of the success and abnormality evaluation of the synergy function to establish a causal relationship; Merging the connection association with the causal relationship to construct the causal association library; According to the module connection relationship, a connection association is obtained, including: Constructing an adjacency matrix according to the module connection relationship; Extract the type and weight of each module connection and configure the connection properties; Configuring connection weights according to the connection attributes; The adjacency matrix is ​​converted into a weighted graph based on the connection weights to obtain the connection association, wherein the modules in the weighted graph are nodes, the connection edge weights represent the connection strength between the connection modules, and the connection association is used to represent the connection strength between the modules.

2. The monitoring and early warning method for skid-mounted equipment according to claim 1 is characterized in that: Causal relationship analysis is performed based on the influencing factors of the success and abnormality evaluation of the synergistic function to establish causal relationships, including: Decomposing the influencing factors according to the evaluation results of the success and abnormality of the collaborative function to obtain a success factor set and an abnormal factor set; Based on the success factor set and the abnormal factor set, factor contribution is calculated by using mean square error; generating an initial causal diagram based on the factor contributions; Based on historical sample data, through time series causal analysis, the impact correlation of each factor on the synergistic function results is explored; An initial cause-effect graph is optimized according to the impact correlation to obtain the cause-effect relationship.

3. The monitoring and early warning method for skid-mounted equipment according to claim 2 is characterized in that: Based on the historical sample data, through time series causal analysis, the influence correlation of each factor on the synergistic function results is explored, including: Setting a dynamic time window and a factor variable screening gradient, wherein the dynamic time window is used to perform an impact correlation analysis of multiple time lengths, and the factor variable screening gradient is used to control the continuous increase in the number of factors; Variables are set according to the dynamic time window and factor variable screening gradient, and the dependency of each factor on the synergistic function result is identified through the time series analysis network model to obtain the influence correlation of each factor or factor combination on the synergistic function result.

4. The monitoring and early warning method for skid-mounted equipment according to claim 1 is characterized in that: The causal association library is disassembled and clustered according to the input data, data analysis, and result output logic framework to obtain clustering results and corresponding relationship identifiers, including: Decompose the causal relationship of each functional block according to the input data, data analysis, and result output logic framework, and determine the causal relationship of input data-data processing-result output of each functional block; Based on the causal relationship of input data-data processing-result output of each functional block, an attribute matrix is ​​constructed to record the relationship identification of each node, where the row represents the module and the column represents the relationship identification type; According to the input data and the data source of the data analysis, a dependency graph is constructed, the influence of the data source on the functional block is calculated, and the dependency influence weight is allocated; According to the dependency influence weights of the data sources on the functional blocks, a cross-weight matrix is ​​constructed to identify the cross-influence relationship; A clustering is performed based on the attribute matrix, and a secondary clustering is performed based on the cross weight matrix to obtain the clustering result.

5. The monitoring and early warning method for skid-mounted equipment according to claim 4 is characterized in that: According to the clustering results and the corresponding relationship identifiers, a warning path search is performed based on the causal association library to determine the graded warning information, including: Performing standardization processing on the same data source according to the clustering result, and establishing a connection between the data source and the input data of the functional block; Based on the clustering result, taking the input end of the data source as the starting point, performing path search according to the causal association library, determining the target early warning function block, and obtaining the influence weight of the target early warning function block according to the correlation between the search path and the path in the causal association library, wherein the target early warning function block includes a single device or a combination of devices; The graded warning information is determined based on the total amount of influence weights of the target warning function block in the search path.

6. A monitoring and early warning device for skid-mounted equipment, characterized in that: The device is used to implement the monitoring and early warning method for skid-mounted equipment according to any one of claims 1 to 5, and the device comprises: The causal association library construction module is used to perform functional coordination and fault impact causal relationship analysis based on the collaborative functional blocks of the skid-mounted equipment, and to build a causal association library; A relationship identification acquisition module is used to disassemble and cluster the causal association library according to the input data, data analysis, and result output logic framework to obtain clustering results and corresponding relationship identifications, wherein the relationship identifications include input relationship identifications, processing relationship identifications, and output relationship identifications, wherein the clustering processing includes: clustering the attributes of functional similarity according to the causal relationship of the functional blocks, clustering the cross-influence relationships according to the data source dependency based on the attribute clustering results, identifying the cross-influence strength of the causal relationship, obtaining clustering results, and generating relationship identifications of causal relationship nodes according to the clustering results; A hierarchical warning information determination module, configured to search for warning paths based on the causal association library according to the clustering results and corresponding relationship identifiers, and determine hierarchical warning information; The early warning identification result acquisition module is used to perform early warning monitoring of the collaborative functional blocks of the skid-mounted equipment according to the relationship identifier and the hierarchical early warning information to obtain the early warning identification result.

Images