Fuel gas system comprehensive management method based on cloud platform

Abstract

The invention relates to the technical field of fuel gas system management, in particular to a fuel gas system comprehensive management method based on a cloud platform, which comprises the following steps of: acquiring data of each node of a high-pressure fuel gas system and a low-pressure fuel gas system in real time through a sensor network of the fuel gas system, and uploading the data to the cloud platform; the collected data of the high-pressure gas system and the low-pressure gas system are classified, stored and managed; carrying out fusion processing on the data of the high-voltage system and the low-voltage system, and identifying relevance and difference; early warning information for a high-voltage system and a low-voltage system is automatically generated; based on the early warning information and the real-time data, the cloud platform automatically or manually intervenes and adjusts operation parameters of the high-pressure system and the low-pressure system through a collaborative scheduling algorithm so as to ensure overall coordination and optimization of the systems, and collaborative scheduling comprises pressure adjustment and flow distribution between the high-pressure system and the low-pressure system. According to the invention, the operation efficiency of the gas system is improved, the energy consumption of the system can be effectively reduced, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of gas system management, and in particular to a comprehensive management method for a gas system based on a cloud platform. Background Art

[0002] With the continuous development of modern society, gas systems have become an important part of daily life and industrial production. However, traditional gas systems have many problems in management and monitoring, mainly including the following aspects:

[0003] Existing gas system management methods are mostly passive responses, that is, they are handled after problems occur, and lack active early warning and intelligent scheduling mechanisms. Especially in emergency situations such as gas leaks, gas peaks and equipment failures, the response speed and processing capabilities of traditional management methods often cannot meet actual needs, posing a major safety hazard.

[0004] High-pressure and low-pressure gas systems usually operate independently and lack an effective coordinated scheduling mechanism, resulting in uneven resource utilization and inefficient system efficiency. There are significant differences between high-pressure and low-pressure systems in terms of pressure regulation, flow control, safety monitoring, etc. The traditional separation management model makes it difficult to achieve overall optimization and collaborative work.

[0005] Insufficient data analysis capabilities: Traditional gas system monitoring data is mostly presented in the form of simple alarms and reports, lacking in-depth data analysis and mining capabilities, and unable to identify deep-seated problems and potential risks in system operation. The lack of data analysis tools means that managers lack scientific basis in the decision-making process, making it difficult to carry out effective system optimization. Summary of the invention

[0006] Based on the above objectives, the present invention provides a comprehensive management method for a gas system based on a cloud platform.

[0007] The integrated management method of the gas system based on the cloud platform includes the following steps:

[0008] S1, collects data from each node of the high-pressure and low-pressure gas systems in real time through the gas system's sensor network, including pressure, flow, temperature and gas composition parameters, and uploads the data to the cloud platform. The data collected by the high-pressure system includes the pressure, flow and temperature parameters of the high-pressure pipe network; the data collected by the low-pressure system includes the pressure, flow and temperature parameters of the low-pressure pipe network;

[0009] S2, using the big data storage function of the cloud platform to classify, store and manage the collected data of the high-pressure and low-pressure gas systems;

[0010] S3, data fusion and analysis: Through the intelligent analysis module of the cloud platform, the data of the high-voltage and low-voltage systems are fused and processed, the correlation and difference are identified, and a comprehensive analysis report is generated. Data fusion adopts multi-source data fusion technology to uniformly process data from different sources and types to ensure the accuracy of the analysis results;

[0011] S4, based on the data analysis results, the cloud platform automatically generates warning information for high-pressure and low-pressure systems, including abnormal pressure, abnormal flow, and abnormal gas composition;

[0012] S5, Collaborative dispatch and control: Based on early warning information and real-time data, the cloud platform automatically or manually adjusts the operating parameters of the high-pressure and low-pressure systems through collaborative dispatch algorithms to ensure the overall coordination and optimization of the system. Collaborative dispatch includes pressure regulation and flow distribution between the high-pressure system and the low-pressure system.

[0013] Optionally, the S1 specifically includes:

[0014] Sensor layout: Install pressure sensors, flow sensors, temperature sensors and gas composition analyzers at key nodes of the high-pressure and low-pressure pipeline networks to obtain pressure data, flow data, temperature data and gas composition data of the high-pressure and low-pressure pipeline networks. The gas composition data includes methane content, hydrogen content and carbon dioxide content.

[0015] Data acquisition unit: Each sensor is connected to the data acquisition unit through wireless communication. The data acquisition unit is responsible for collecting data from each sensor in real time, converting the data format, packaging the processed data and transmitting it to the cloud platform.

[0016] Optionally, the S2 specifically includes:

[0017] S21, data partitioning: the data of the high-pressure gas system and the low-pressure gas system are divided into different storage partitions, the data partition of the high-pressure system stores the pressure, flow, temperature and gas composition data of the high-pressure pipe network; the data partition of the low-pressure system stores the pressure, flow, temperature and gas composition data of the low-pressure pipe network;

[0018] S22, data label and metadata management: add labels and metadata to each data record for easy classification and query. The labels include data type (pressure, flow, temperature, gas composition), data source (high pressure system or low pressure system), timestamp, and geographic location;

[0019] S23, distributed storage architecture: Distributed storage architecture is used to store data on multiple nodes. The distributed storage architecture uses Hadoop HDFS technology to achieve distributed storage of data;

[0020] S24, compressing the stored data and backing up the data regularly to ensure that the data can be restored in case of failure;

[0021] S25, establish data index, which is based on data type, data source, timestamp, and geographic location fields to achieve fast query and retrieval.

[0022] Optionally, the data fusion and analysis in S3 specifically includes:

[0023] S31, using multi-source data fusion technology, fuses different types of data from high-pressure and low-pressure systems. Data fusion includes time alignment, space alignment and semantic alignment, ensuring that data from different data sources can be compared and analyzed in the same time and space dimensions. Time alignment ensures that the data of high-pressure and low-pressure systems have consistent timestamps, space alignment ensures that the geographical locations corresponding to the data are consistent, and semantic alignment ensures that the meaning of the data is consistent.

[0024] S32, correlation analysis: Through the intelligent analysis module, the fused data is analyzed for correlation, the correlation between the high-pressure and low-pressure systems is identified, and the causal analysis method is used to perform correlation analysis to find out the key factors affecting the operation of the high-pressure and low-pressure systems;

[0025] S33, difference analysis: perform difference analysis on the data of high-pressure and low-pressure systems, identify differences and abnormalities in system operation, and use trend analysis methods to perform difference analysis to find inconsistencies and potential problems in system operation;

[0026] S34, comprehensive analysis report generation: based on the results of the correlation and difference analysis, a comprehensive analysis report is automatically generated, and the report includes the analysis results.

[0027] Optionally, the causal analysis is used to determine a time series X t Does it help predict another time series Y t , including:

[0028] Let Y t and X t There are two time series, and the following regression analysis is performed:

[0029] Among them, Y t is the dependent variable (e.g. flow rate of a low pressure system), X t is the independent variable (e.g., the pressure of the high-pressure system), α0 is the intercept term, and α i and β j is the regression coefficient, ∈ t is the error term, p and q are the number of lag terms, and in this model, the dependent variable Yt is its own lag term Y t-i and the independent variable X t The lag term X t-j jointly explained;

[0030] Among them, γ0 is the intercept term, γ i is the regression coefficient, η t is the error term. In this model, the dependent variable Y t Only its own lagged term Y t-i Explanation, regardless of the independent variable X t The impact of

[0031] By comparing whether it contains or not contains X t The predictive ability of the two regression models is tested by using the F test and calculating the F statistic: Among them, RSS r is the residual sum of squares of the restricted model, RSS u is the residual sum of squares of the complete model, n is the number of samples, and if the p-value of the F statistic is less than the significance level (such as 0.05), then X is considered t Lead to Y t , that is, X t Provides information about Y t The useful information of the future value of X t Prior to Y t And can be used to predict Y t By comparing the predictive power of the two models (measured by the change in the residual sum of squares), we can determine whether the independent variable X t Does it significantly improve the dependent variable Y t The predictive power of t The full model significantly outperforms the model without X t , then we assume that X t Lead to Y t .

[0032] Optionally, the trend analysis uses a weighted moving average method to smooth the data and identify the data change trend. Suppose the data sequence is D t , weighted moving average The expression is:

[0033] in, is the weighted moving average at time point t, w i is the weight, which can be linearly decreasing: w i =ni.

[0034] Optionally, the cloud platform automatically generates early warning information for high-pressure and low-pressure systems according to the data analysis results in S4, specifically including:

[0035] S41, threshold setting: according to historical data, set the normal range and warning threshold of key parameters (pressure, flow, gas composition) of high-pressure and low-pressure systems. The thresholds include upper and lower limits, which are used to judge whether the system is running normally:

[0036] High pressure system pressure threshold: and

[0037] Low pressure system pressure threshold: and

[0038] High pressure system flow threshold: and

[0039] Low pressure system flow threshold: and

[0040] Gas component concentration threshold: and (where i represents different gas components, such as methane, hydrogen, and carbon dioxide);

[0041] S42, real-time monitoring: The cloud platform monitors the key parameters of the high-pressure and low-pressure systems in real time through a sensor network and compares the collected data with the preset thresholds;

[0042] Real-time monitoring of high pressure system pressure P H (t), flow rate F H (t), gas component concentration

[0043] Real-time monitoring of low pressure system pressure P L (t), flow rate F L (t), gas component concentration

[0044] S43, anomaly detection: the cloud platform analyzes the real-time monitoring data and identifies anomalies that exceed the threshold range;

[0045] S44, warning information generation: When an abnormal situation is detected, the cloud platform automatically generates warning information, including abnormal parameters, abnormal type, abnormal value and its timestamp information.

[0046] Optionally, the coordinated scheduling and control in S5 specifically includes:

[0047] S51, analyzing the warning information, identifying the abnormal type (such as abnormal pressure, abnormal flow, abnormal gas composition), abnormal location (high pressure system or low pressure system), abnormal time and abnormal value;

[0048] S52, real-time data acquisition: obtain the real-time operation data of the current high-pressure and low-pressure systems from the cloud platform, including pressure and flow parameters:

[0049] High pressure system: pressure P H (t), flow rate F H (t);

[0050] Low pressure system: pressure P L (t), flow rate F L (t);

[0051] S53, collaborative scheduling algorithm: Use a collaborative scheduling method based on a model predictive control algorithm to optimize scheduling based on early warning information and real-time data:

[0052] Optimization goals: minimize total system energy consumption, maximize system stability, and ensure gas supply security;

[0053] Constraints: Ensure that the pressure and flow of high-pressure and low-pressure systems operate within the safety threshold range.

[0054] Optionally, the model predictive control algorithm specifically includes:

[0055] State-space model:

[0056] Define the state variables x(t) of the system, including the pressure and flow of the high-pressure system and the low-pressure system;

[0057] Define the control input u(t), including the adjustment parameters of the high-pressure system and the low-pressure system;

[0058] System dynamic equation: x(t+1)=Ax(t)+Bu(t)+w(t), where A and B are system matrices and w(t) is process noise;

[0059] Optimization problem:

[0060] Define the performance indicator function J: Where N is the prediction time domain length, Q and R are weight matrices used to balance the influence of system state and control input;

[0061] Constraints:

[0062]

[0063] Use the online optimization algorithm to solve the optimization problem and get the optimal control input u * (t);

[0064] According to the optimal control input u * (t), the cloud platform automatically adjusts the operating parameters of the high-pressure and low-pressure systems.

[0065] Optionally, the collaborative scheduling and control also includes feedback of scheduling results, real-time monitoring of scheduling results, evaluation of scheduling effects, and re-scheduling optimization if new anomalies or unexpected situations occur. The adjusted system state x(t+1) is monitored to evaluate whether the optimization objectives and constraints are met. If not, the collaborative scheduling algorithm is re-executed until the system state is stable.

[0066] Beneficial effects of the present invention:

[0067] The present invention monitors the pressure, flow and gas component concentration of the high-pressure and low-pressure systems in real time, and performs abnormal detection in combination with set thresholds. The cloud platform can promptly discover and warn of abnormal conditions in the operation of the system (such as abnormal pressure, abnormal flow and abnormal gas composition). This timely warning mechanism effectively prevents potential safety hazards and ensures the safe operation of the gas system under various working conditions. The collaborative scheduling method based on the model predictive control algorithm optimizes the real-time data of the high-pressure and low-pressure systems, automatically or manually intervenes to adjust the operating parameters of the system, and ensures the overall coordination and optimization of the system. It not only improves the stability of the system, but also can quickly respond and adjust under abnormal conditions, further ensuring the safety of the system.

[0068] The present invention enables the data of high-pressure and low-pressure systems to be uniformly processed and analyzed on the same platform. Through cause-and-effect analysis and trend analysis, the cloud platform can identify key factors and potential problems that affect system operation. The analysis results provide a scientific basis for optimization, helping managers make more informed decisions. The collaborative scheduling algorithm automatically solves the optimal control input under the optimization objectives and constraints, adjusts the pressure, flow and gas component concentration of the high-pressure and low-pressure systems, and the intelligent scheduling optimization not only improves the operating efficiency of the gas system, but also effectively reduces the energy consumption of the system and reduces operating costs.

[0069] The present invention uses the big data storage function of the cloud platform to classify, store and manage the real-time data of the high-voltage and low-voltage systems to ensure the integrity and security of the data. The distributed storage architecture ensures high availability and fast access to data and supports real-time data sharing by multiple terminals and multiple users. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0071] Figure 1 A schematic diagram of a comprehensive management method flow chart of an embodiment of the present invention;

[0072] Figure 2 Schematic diagram of data fusion and analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0074] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0075] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0076] like Figure 1-Figure 2 As shown, the integrated management method of the gas system based on the cloud platform includes the following steps:

[0077] S1, collects data from each node of the high-pressure and low-pressure gas systems in real time through the gas system's sensor network, including pressure, flow, temperature and gas composition parameters, and uploads the data to the cloud platform. The data collected by the high-pressure system includes the pressure, flow and temperature parameters of the high-pressure pipe network; the data collected by the low-pressure system includes the pressure, flow and temperature parameters of the low-pressure pipe network;

[0078] S2, using the big data storage function of the cloud platform, classifies, stores and manages the collected data of the high-pressure and low-pressure gas systems to ensure the integrity and security of the data. The data storage adopts a distributed storage architecture to ensure high availability and fast access to the data;

[0079] S3, data fusion and analysis: Through the intelligent analysis module of the cloud platform, the data of the high-voltage and low-voltage systems are fused and processed, the correlation and difference are identified, and a comprehensive analysis report is generated. Data fusion adopts multi-source data fusion technology to uniformly process data from different sources and types to ensure the accuracy of the analysis results;

[0080] S4, based on the data analysis results, the cloud platform automatically generates warning information for high-pressure and low-pressure systems, and notifies relevant personnel through SMS, email or APP push, etc. The warning information includes abnormal pressure, abnormal flow, and abnormal gas composition;

[0081] S5, Collaborative dispatch and control: Based on early warning information and real-time data, the cloud platform automatically or manually adjusts the operating parameters of the high-pressure and low-pressure systems through collaborative dispatch algorithms to ensure the overall coordination and optimization of the system. Collaborative dispatch includes pressure regulation and flow distribution between the high-pressure system and the low-pressure system.

[0082] S1 specifically includes:

[0083] Sensor layout: Install pressure sensors, flow sensors, temperature sensors and gas composition analyzers at key nodes of the high-pressure and low-pressure pipeline networks to obtain pressure data, flow data, temperature data and gas composition data of the high-pressure and low-pressure pipeline networks. The gas composition data includes methane content, hydrogen content and carbon dioxide content.

[0084] Data acquisition unit: Each sensor is connected to the data acquisition unit through wireless communication. The data acquisition unit is responsible for collecting data from each sensor in real time, converting the data format, packaging the processed data and transmitting it to the cloud platform.

[0085] S2 specifically includes:

[0086] S21, data partitioning: the data of the high-pressure gas system and the low-pressure gas system are divided into different storage partitions, the data partition of the high-pressure system stores the pressure, flow, temperature and gas composition data of the high-pressure pipe network; the data partition of the low-pressure system stores the pressure, flow, temperature and gas composition data of the low-pressure pipe network;

[0087] S22, data label and metadata management: add labels and metadata to each data record for easy classification and query. The labels include data type (pressure, flow, temperature, gas composition), data source (high pressure system or low pressure system), timestamp, and geographic location;

[0088] S23, Distributed Storage Architecture: Distributed storage architecture is used to store data on multiple nodes to ensure high availability and fast access to data. The distributed storage architecture uses Hadoop HDFS technology to achieve distributed storage of data;

[0089] S24, compressing the stored data and backing up the data regularly to ensure that the data can be restored in case of failure;

[0090] S25, establish data index, which is based on data type, data source, timestamp, and geographic location fields to achieve fast query and retrieval.

[0091] Data fusion and analysis in S3 specifically include:

[0092] S31, using multi-source data fusion technology, fuses different types of data from high-pressure and low-pressure systems. Data fusion includes time alignment, space alignment and semantic alignment, ensuring that data from different data sources can be compared and analyzed in the same time and space dimensions. Time alignment ensures that the data of high-pressure and low-pressure systems have consistent timestamps, space alignment ensures that the geographical locations corresponding to the data are consistent, and semantic alignment ensures that the meaning of the data is consistent.

[0093] Time alignment: Ensure that the data of the high-voltage and low-voltage systems have consistent timestamps. Let the data of the high-voltage system be D H And the data of low pressure system is D L , where each data record has a timestamp t;

[0094] The time alignment method uses linear interpolation, that is, interpolation calculation is performed based on the data of two adjacent time points to obtain data with a unified timestamp:

[0095] Among them, t i and t i+1 are two adjacent time points, D(t i ) and D(t i+1 ) is the corresponding sensor data, and t is the target timestamp.

[0096] Spatial Alignment:

[0097] Ensure that the geographical location corresponding to the data is consistent. Suppose the geographical location data of the high-voltage system is L H The geographical location data of the low pressure system is L L;

[0098] The spatial alignment method uses the nearest neighbor interpolation method, that is, interpolation calculation is performed based on the nearest neighbor point of the geographical location:

[0099] D aligned (L) = ∑ i w i ·D(L i ), where L i is the geographical location closest to the target location L, w i is the corresponding weight, satisfying ∑ i w i =1;

[0100] Semantic alignment:

[0101] Ensure that the meaning of the data is consistent. Data from different sources may differ in units, formats, and naming, and need to be processed uniformly. The semantic alignment method uses unit conversion and standardization, such as converting pressure values ​​in different units into standard units.

[0102] S32, correlation analysis: Through the intelligent analysis module, the fused data is analyzed for correlation, the correlation between the high-pressure and low-pressure systems is identified, and the causal analysis method is used to perform correlation analysis to find out the key factors affecting the operation of the high-pressure and low-pressure systems;

[0103] S33, difference analysis: perform difference analysis on the data of high-pressure and low-pressure systems, identify differences and abnormalities in system operation, and use trend analysis methods to perform difference analysis to find inconsistencies and potential problems in system operation;

[0104] S34, comprehensive analysis report generation: Based on the results of correlation and difference analysis, a comprehensive analysis report is automatically generated. The report includes the analysis results to help managers fully understand the operating status of the high-pressure and low-pressure systems.

[0105] Causal analysis is used to determine whether a time series X t Does it help predict another time series Y t , including:

[0106] Let Y t and X t They are two time series, comparing the two regression models, and performing the following regression analysis:

[0107] Among them, Y t is the dependent variable (e.g. flow rate of a low pressure system), X t is the independent variable (e.g., the pressure of the high-pressure system), α0 is the intercept term, and α i and βj is the regression coefficient, ∈ t is the error term, p and q are the number of lag terms, and in this model, the dependent variable Y t is its own lag term Y t-i and the independent variable X t The lag term X t-j jointly explained;

[0108] Among them, γ0 is the intercept term, γ i is the regression coefficient, η t is the error term. In this model, the dependent variable Y t Only its own lagged term Y t-i Explanation, regardless of the independent variable X t The impact of

[0109] By comparing whether it contains or not contains X t The predictive ability of the two regression models is tested by using the F test and calculating the F statistic: Among them, RSS r is the residual sum of squares of the restricted model, RSS u is the residual sum of squares of the complete model, n is the number of samples, and if the p-value of the F statistic is less than the significance level (such as 0.05), then X is considered t Lead to Y t , that is, X t Provides information about Y t The useful information of the future value of X t Prior to Y t And can be used to predict Y t By comparing the predictive power of the two models (measured by the change in the residual sum of squares), we can determine whether the independent variable X t Does it significantly improve the dependent variable Y t The predictive power of t The full model significantly outperforms the model without X t , then we assume that X t Lead to Y t .

[0110] Trend analysis uses weighted moving average method to smooth data and identify data change trends. Let the data sequence be D t , weighted moving average The expression is:

[0111] in, is the weighted moving average at time point t, w i is the weight, which can be linearly decreasing: w i =ni.

[0112] The analysis results include:

[0113] Causal analysis results: List the key factors found through causal relationship test and their impact on system operation, and show the causal relationship between various parameters in the form of a table. For example, the impact of high-pressure system pressure changes on low-pressure system flow can be expressed in the following table:

[0114] causation Regression coefficient P-value F-test results <![CDATA[P H →F L ]]> <![CDATA[β j ]]> p→value F→statistic

[0115] In the table, P H Indicates the pressure of the high pressure system, F L Represents the flow rate of the low-pressure system, the causal relationship P H →F L It indicates whether the pressure change of the high-pressure system can lead to the flow change of the low-pressure system, that is, whether the past value of the high-pressure system pressure can be used to predict the flow of the low-pressure system. Through regression analysis, the regression coefficient (□□) and related statistics (such as p-value and F test result) can be calculated to determine whether the pressure of the high-pressure system has a significant impact on the flow of the low-pressure system.

[0116] Trend analysis results: Displays trend graphs obtained through weighted moving average method to identify inconsistencies and potential problems in system operation.

[0117] Conclusion and recommendations: Improvement suggestions and optimization measures are proposed based on the analysis results. For example, based on the causal analysis results, it is recommended to adjust the high-pressure system pressure in a specific time period to balance the low-pressure system flow; based on the trend analysis results, it is recommended to increase the monitoring frequency during system operation to provide early warning of potential problems.

[0118] According to the data analysis results in S4, the cloud platform automatically generates early warning information for high-pressure and low-pressure systems, including:

[0119] S41, threshold setting: according to historical data, set the normal range and warning threshold of key parameters (pressure, flow, gas composition) of high-pressure and low-pressure systems. The thresholds include upper and lower limits, which are used to judge whether the system is running normally:

[0120] High pressure system pressure threshold: and

[0121] Low pressure system pressure threshold: and

[0122] High pressure system flow threshold: and

[0123] Low pressure system flow threshold: and

[0124] Gas component concentration threshold: and (where i represents different gas components, such as methane, hydrogen, and carbon dioxide);

[0125] S42, real-time monitoring: The cloud platform monitors the key parameters of the high-pressure and low-pressure systems in real time through a sensor network and compares the collected data with the preset thresholds;

[0126] Real-time monitoring of high pressure system pressure P H (t), flow rate F H (t), gas component concentration

[0127] Real-time monitoring of low pressure system pressure P L (t), flow rate F L (t), gas component concentration

[0128] S43, anomaly detection: the cloud platform analyzes the real-time monitoring data and identifies anomalies that exceed the threshold range;

[0129] Pressure abnormality detection: If or The high pressure system pressure is considered abnormal; if or It is considered that the low-pressure system pressure is abnormal;

[0130] Traffic anomaly detection: If or The high pressure system flow is considered abnormal; if or It is considered that the flow rate of the low-pressure system is abnormal;

[0131] Gas composition abnormality detection: If or It is considered that the gas composition of the high pressure system is abnormal; if or It is considered that the gas composition of the low-pressure system is abnormal.

[0132] S44, warning information generation: When an abnormal situation is detected, the cloud platform automatically generates warning information, including abnormal parameters, abnormal type, abnormal value and its timestamp information.

[0133] Warning information format:

[0134] Abnormal type: abnormal pressure, abnormal flow, abnormal gas composition;

[0135] Abnormal parameters;

[0136] Abnormal value: abnormal value detected in real time;

[0137] Timestamp: the time when the exception occurred;

[0138] System status: high pressure system or low pressure system.

[0139] The coordinated scheduling and control in S5 specifically include:

[0140] S51, analyzing the warning information, identifying the abnormal type (such as abnormal pressure, abnormal flow, abnormal gas composition), abnormal location (high pressure system or low pressure system), abnormal time and abnormal value;

[0141] S52, real-time data acquisition: obtain the real-time operation data of the current high-pressure and low-pressure systems from the cloud platform, including pressure and flow parameters:

[0142] High pressure system: pressure P H (t), flow rate F H (t);

[0143] Low pressure system: pressure P L (t), flow rate F L (t);

[0144] S53, collaborative scheduling algorithm: Use a collaborative scheduling method based on a model predictive control algorithm to optimize scheduling based on early warning information and real-time data:

[0145] Optimization goals: minimize total system energy consumption, maximize system stability, and ensure gas supply security;

[0146] Constraints: Ensure that the pressure and flow of high-pressure and low-pressure systems operate within the safety threshold range.

[0147] The model predictive control algorithm specifically includes:

[0148] State-space model:

[0149] Define the state variables x(t) of the system, including the pressure and flow of the high-pressure system and the low-pressure system:

[0150]

[0151] Define the control input u(t), including the adjustment parameters of the high-pressure system and the low-pressure system:

[0152]

[0153] System dynamic equation: x(t+1)=Ax(t)+Bu(t)+w(t), where A and B are system matrices and w(t) is process noise;

[0154] Optimization problem:

[0155] Define the performance indicator function J: Where N is the prediction time domain length, Q and R are weight matrices used to balance the influence of system state and control input;

[0156] Constraints:

[0157]

[0158] Use the online optimization algorithm to solve the optimization problem and get the optimal control input u * (t);

[0159] According to the optimal control input u * (t), the cloud platform automatically adjusts the operating parameters of the high-pressure and low-pressure systems to ensure overall coordination and optimization, that is, the system automatically sends control instructions to each regulating device to adjust the pressure and flow of the high-pressure and low-pressure systems.

[0160] Collaborative scheduling and control also includes feedback of scheduling results, real-time monitoring of scheduling results, and evaluation of scheduling effects. If new anomalies or unexpected situations occur, re-scheduling optimization is performed, the adjusted system state x(t+1) is monitored, and whether the optimization objectives and constraints are met. If not, the collaborative scheduling algorithm is re-executed until the system state is stable.

[0161] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0162] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A comprehensive management method for a gas system based on a cloud platform, characterized in that: The following steps are involved: S1, collects data from each node of the high-pressure and low-pressure gas systems in real time through the gas system's sensor network, including pressure, flow, temperature and gas composition parameters, and uploads the data to the cloud platform. The data collected by the high-pressure system includes the pressure, flow and temperature parameters of the high-pressure pipe network; the data collected by the low-pressure system includes the pressure, flow and temperature parameters of the low-pressure pipe network; S2, using the big data storage function of the cloud platform to classify, store and manage the collected data of the high-pressure and low-pressure gas systems; S3, data fusion and analysis: Through the intelligent analysis module of the cloud platform, the data of the high-voltage and low-voltage systems are fused and processed, the correlation and difference are identified, and a comprehensive analysis report is generated. Data fusion adopts multi-source data fusion technology to uniformly process data from different sources and types; S4, based on the data analysis results, the cloud platform automatically generates warning information for high-pressure and low-pressure systems, including abnormal pressure, abnormal flow, and abnormal gas composition; S5, Collaborative dispatch and control: Based on early warning information and real-time data, the cloud platform automatically or manually adjusts the operating parameters of the high-pressure and low-pressure systems through collaborative dispatch algorithms to ensure the overall coordination and optimization of the system. Collaborative dispatch includes pressure regulation and flow distribution between the high-pressure system and the low-pressure system.

2. The integrated management method of a gas system based on a cloud platform according to claim 1, characterized in that: The S1 specifically includes: Sensor layout: Install pressure sensors, flow sensors, temperature sensors and gas composition analyzers at key nodes of the high-pressure and low-pressure pipeline networks to obtain pressure data, flow data, temperature data and gas composition data of the high-pressure and low-pressure pipeline networks. The gas composition data includes methane content, hydrogen content and carbon dioxide content. Data acquisition unit: Each sensor is connected to the data acquisition unit through wireless communication. The data acquisition unit is responsible for collecting data from each sensor in real time, converting the data format, packaging the processed data and transmitting it to the cloud platform.

3. The integrated management method of a gas system based on a cloud platform according to claim 1, characterized in that: The S2 specifically includes: S21, data partitioning: the data of the high-pressure gas system and the low-pressure gas system are divided into different storage partitions, the data partition of the high-pressure system stores the pressure, flow, temperature and gas composition data of the high-pressure pipe network; the data partition of the low-pressure system stores the pressure, flow, temperature and gas composition data of the low-pressure pipe network; S22, data label and metadata management: add labels and metadata to each data record to facilitate classification and query. The labels include data type, data source, timestamp, and geographic location; S23, distributed storage architecture: Distributed storage architecture is used to store data on multiple nodes. The distributed storage architecture uses Hadoop HDFS technology to achieve distributed storage of data; S24, compressing the stored data and backing up the data regularly to ensure that the data can be restored in case of failure; S25, establish data index, which is based on data type, data source, timestamp, and geographic location fields to achieve fast query and retrieval.

4. The integrated management method of a gas system based on a cloud platform according to claim 1, characterized in that: The data fusion and analysis in S3 specifically include: S31, using multi-source data fusion technology, different types of data from high-pressure and low-pressure systems are fused and processed. Data fusion includes time alignment, space alignment and semantic alignment, ensuring that data from different data sources can be compared and analyzed in the same time and space dimensions. Time alignment ensures that the data of high-pressure and low-pressure systems have consistent timestamps, space alignment ensures that the geographical locations corresponding to the data are consistent, and semantic alignment ensures that the meaning of the data is consistent; S32, correlation analysis: Through the intelligent analysis module, the fused data is analyzed for correlation, the correlation between the high-pressure and low-pressure systems is identified, and the cause-effect analysis method is used to perform correlation analysis to find out the key factors affecting the operation of the high-pressure and low-pressure systems; S33, difference analysis: perform difference analysis on the data of high-pressure and low-pressure systems, identify the differences and abnormalities in system operation, and use trend analysis methods to perform difference analysis to find inconsistencies and potential problems in system operation; S34, comprehensive analysis report generation: based on the results of the correlation and difference analysis, a comprehensive analysis report is automatically generated, and the report includes the analysis results.

5. The integrated management method of a gas system based on a cloud platform according to claim 4 is characterized in that: The causal analysis is used to determine a time series X t Does it help predict another time series Y t , specifically including: Let Y t and X t There are two time series, and the following regression analysis is performed: Among them, Y t is the dependent variable, X t is the independent variable, α0 is the intercept term, α i and β j is the regression coefficient, ∈ t is the error term, p and q are the number of lag terms; Among them, γ0 is the intercept term, γ i is the regression coefficient, η t is the error term; By comparing whether it contains or not contains X t The predictive ability of the two regression models is tested by using the F test and calculating the F statistic: Among them, RSS r is the residual sum of squares of the restricted model, RSS u is the residual sum of squares of the complete model, n is the number of samples, and if the p-value of the F statistic is less than the significance level, then X is considered t Lead to Y t , that is, X t Provides information about Y t The useful information of the future value of X t Prior to Y t And can be used to predict Y t .

6. The integrated management method of a gas system based on a cloud platform according to claim 5, characterized in that: The trend analysis uses weighted moving average method to smooth the data and identify the trend of data changes. Suppose the data sequence is D t , weighted moving average The expression is: in, is the weighted moving average at time point t, w i is the weight.

7. The integrated management method of a gas system based on a cloud platform according to claim 6 is characterized in that: In S4, according to the data analysis results, the cloud platform automatically generates early warning information for the high-pressure and low-pressure systems, specifically including: S41, threshold setting: according to historical data, set the normal range and warning threshold of each key parameter of the high-pressure and low-pressure systems. The thresholds include upper and lower limits, which are used to determine whether the system is operating normally: High pressure system pressure threshold: and Low pressure system pressure threshold: and High pressure system flow threshold: and Low pressure system flow threshold: and Gas component concentration threshold: and S42, real-time monitoring: The cloud platform monitors the key parameters of the high-pressure and low-pressure systems in real time through a sensor network and compares the collected data with the preset thresholds; Real-time monitoring of high pressure system pressure P H (t), flow rate F H (t), gas component concentration Real-time monitoring of low pressure system pressure P L (t), flow rate F L (t), gas component concentration S43, anomaly detection: the cloud platform analyzes the real-time monitoring data and identifies anomalies that exceed the threshold range; S44, warning information generation: When an abnormal situation is detected, the cloud platform automatically generates warning information, including abnormal parameters, abnormal type, abnormal value and its timestamp information.

8. The integrated management method of a gas system based on a cloud platform according to claim 1, characterized in that: The coordinated scheduling and control in S5 specifically includes: S51, analyzing the warning information, identifying the abnormal type, abnormal location, abnormal time and abnormal value; S52, real-time data acquisition: obtain the real-time operation data of the current high-pressure and low-pressure systems from the cloud platform, including pressure and flow parameters: High pressure system: pressure P H (t), flow rate F H (t); Low pressure system: pressure P L (t), flow rate F L (t); S53, collaborative scheduling algorithm: Use a collaborative scheduling method based on a model predictive control algorithm to optimize scheduling based on early warning information and real-time data: Optimization goals: minimize total system energy consumption, maximize system stability, and ensure gas supply security; Constraints: Ensure that the pressure and flow of high-pressure and low-pressure systems operate within the safety threshold range.

9. The integrated management method of a gas system based on a cloud platform according to claim 8, characterized in that: The model predictive control algorithm specifically includes: State-space model: Define the state variables x(t) of the system, including the pressure and flow of the high-pressure system and the low-pressure system; Define the control input u(t), including the adjustment parameters of the high-pressure system and the low-pressure system; System dynamic equation: x(t+1)=Ax(t)+Bu(t)+w(t), where A and B are system matrices and w(t) is process noise; Optimization problem: Define the performance indicator function J: Where N is the prediction time domain length, Q and R are weight matrices used to balance the influence of system state and control input; Constraints: Use the online optimization algorithm to solve the optimization problem and get the optimal control input u * (t); According to the optimal control input u * (t), the cloud platform automatically adjusts the operating parameters of the high-pressure and low-pressure systems.

10. The integrated management method of a gas system based on a cloud platform according to claim 9, characterized in that: The collaborative scheduling and control also includes feedback of scheduling results, real-time monitoring of scheduling results, and evaluation of scheduling effects. If new anomalies or unexpected situations occur, re-scheduling optimization is performed, the adjusted system state x(t+1) is monitored, and whether the optimization objectives and constraints are met is evaluated. If not, the collaborative scheduling algorithm is re-executed until the system state is stable.

Images