Inorganic salt collection processing monitoring method and device based on digital twinborn technology

Abstract

The invention provides an inorganic salt collecting, processing and monitoring method and device based on a digital twinning technology, and relates to the technical field of inorganic salt production, the inorganic salt collecting, processing and monitoring method based on the digital twinning technology comprises the following steps: constructing a digital twinning simulation model according to parameter information of inorganic salt collecting and processing equipment; acquiring real-time operation data of the inorganic salt collecting and processing equipment and simulation prediction data of the digital twinborn simulation model; based on the real-time operation data and the simulation prediction data, an extreme value theory method and a graph theory algorithm are used for analyzing the abnormity of the inorganic salt collecting and processing equipment; and generating an anomaly analysis report according to an anomaly analysis result of the inorganic salt collection processing equipment. According to the method, the difference between the actual performance and the expected performance of the equipment can be accurately evaluated, so that potential problems can be found in time, continuous optimization of the equipment is facilitated, and the production efficiency and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of inorganic salt production, and in particular to an inorganic salt collection, processing and monitoring method and device based on digital twin technology. Background Art

[0002] Inorganic salt collection and treatment equipment mainly uses the physical properties of liquids that have lower boiling points and are easy to evaporate under vacuum conditions to treat wastewater containing inorganic salts. This equipment collects salt-containing wastewater and heats it under vacuum conditions to evaporate it, thereby separating solid inorganic salts and water vapor. Solid inorganic salts are collected by mechanical equipment during the treatment process and further processed or utilized. At the same time, the water vapor generated by evaporation is effectively collected by the vacuum system, and transferred to the transfer pool after condensation for subsequent treatment. This treatment process can not only effectively recover inorganic salts, but also reduce the total amount of wastewater and increase the reuse rate of water resources. Through this technology, the environmental impact of wastewater treatment can be significantly reduced, while providing reusable raw materials for industrial production, which is in line with the goal of sustainable development.

[0003] In addition, the equipment usually includes a monitoring system to monitor the entire evaporation process in real time to ensure the stability of operation and the optimization of treatment effects. At present, traditional monitoring methods mainly rely on past experience and simple threshold settings, which makes the performance evaluation of the equipment lack of precision. Therefore, it is impossible to effectively predict the actual performance of the equipment under changing operating conditions, resulting in high equipment failure rate and increased maintenance costs. At the same time, traditional methods often focus on the monitoring of a single parameter or component, ignoring the systematic analysis of the equipment as a whole. This limits the comprehensive evaluation of the overall status of the equipment and reduces the effectiveness of preventive maintenance.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of this, the present invention provides an inorganic salt collection, processing and monitoring method and device based on digital twin technology to solve the above-mentioned problems.

[0006] In order to solve the above problems, the specific technical solutions adopted by the present invention are as follows:

[0007] According to one aspect of the present invention, a method for monitoring the collection and processing of inorganic salts based on digital twin technology is provided, and the method for monitoring the collection and processing of inorganic salts based on digital twin technology comprises the following steps:

[0008] S1. Construct a digital twin simulation model based on the parameter information of the inorganic salt collection and processing equipment;

[0009] S2. Obtaining real-time operation data of inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model;

[0010] S3. Based on real-time operation data and simulation prediction data, the extreme value theory method and graph theory algorithm are used to analyze the abnormality of the inorganic salt collection and treatment equipment;

[0011] S4. Generate an abnormal analysis report based on the abnormal analysis results of the inorganic salt collection and treatment equipment.

[0012] Preferably, based on the real-time operation data and the simulation prediction data, the analysis of the abnormality of the inorganic salt collection and treatment equipment using the extreme value theory method and the graph theory algorithm includes the following steps:

[0013] S31, collecting historical operation data of the inorganic salt collection and processing equipment, and using the extreme value theory method to determine the deviation threshold of each operation data of the inorganic salt collection and processing equipment;

[0014] S32, analyzing the dependencies between the components in the inorganic salt collection and processing equipment, and constructing an equipment state diagram according to the dependencies;

[0015] S33. Based on the real-time operation data and simulation prediction data, and according to the deviation threshold and the equipment status diagram, identify and locate the abnormality of the inorganic salt collection and processing equipment.

[0016] Preferably, collecting historical operation data of the inorganic salt collection and treatment equipment and determining the deviation threshold of each operation data of the inorganic salt collection and treatment equipment by using the extreme value theory method comprises the following steps:

[0017] S311, preprocessing the historical operation data of the inorganic salt collection and processing equipment;

[0018] S312, performing descriptive statistical analysis on the preprocessed historical operation data to obtain distribution characteristics of the historical operation data;

[0019] S313. According to the distribution characteristics of the historical operation data, the Hill diagram method in the extreme value theory is used to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment.

[0020] Preferably, performing descriptive statistical analysis on the preprocessed historical operation data to obtain the distribution characteristics of the historical operation data includes the following steps:

[0021] S3121. Calculate the descriptive statistics of the preprocessed historical operation data;

[0022] S3122. Establish a histogram of the preprocessed historical operating data based on descriptive statistics, and calculate the skewness and kurtosis of the operating data;

[0023] S3123. Analyze and interpret descriptive statistics, histograms, skewness and kurtosis to obtain the distribution characteristics of historical operating data.

[0024] Preferably, according to the distribution characteristics of historical operation data, the Hill diagram method in extreme value theory is used to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment, which includes the following steps:

[0025] S3131, sorting the historical operation data in descending order, randomly selecting an initial threshold and calculating the Hill estimator;

[0026] S3132, establishing a Hill graph according to a randomly selected initial threshold and a Hill estimator;

[0027] S3133. Perform a stationarity analysis on the established Hill graph, select the starting point of the stable interval in the Hill graph and use the starting point as the deviation threshold.

[0028] Preferably, the calculation formula for randomly selecting an initial threshold and calculating the Hill estimator is:

[0029]

[0030] In the formula, G k,n represents the Hill estimator;

[0031] k represents the number of data exceeding the initial threshold in the historical operation data;

[0032] n represents the number of historical operation data;

[0033] H(i) represents the i-th operation data in the historical operation data that exceeds the initial threshold;

[0034] H(k) represents the kth operation data in the historical operation data that exceeds the initial threshold.

[0035] Preferably, analyzing the dependencies between components in the inorganic salt collection and treatment equipment and constructing the equipment state diagram according to the dependencies includes the following steps:

[0036] S321. Collect the process flow of the inorganic salt collection and treatment equipment, and analyze the dependencies between the components in the inorganic salt collection and treatment equipment;

[0037] S322, taking each component in the inorganic salt collection and processing equipment as a node, and taking the dependency relationship between the components as an edge;

[0038] S323. Construct a device status diagram between components based on the nodes and edges.

[0039] Preferably, based on the real-time operation data and the simulation prediction data, and according to the deviation threshold and the equipment status diagram, identifying and locating the abnormality of the inorganic salt collection and treatment equipment includes the following steps:

[0040] S331, calculating the absolute value of the deviation between the real-time operation data and the simulation prediction data, and comparing the absolute value of the deviation with the deviation threshold to determine abnormal operation data;

[0041] S332. Identify abnormal operation data in the inorganic salt collection and processing equipment, and based on the equipment status diagram between the various components, identify and locate abnormal equipment in the inorganic salt collection and processing equipment through a matrix algorithm.

[0042] Preferably, identifying abnormal operation data in the inorganic salt collection and treatment equipment, and based on the equipment status diagram between the components, identifying and locating abnormal equipment in the inorganic salt collection and treatment equipment through a matrix algorithm includes the following steps:

[0043] S3321, converting the device state diagram between the components into an adjacency matrix, wherein the rows and columns in the adjacency matrix represent different components in the inorganic salt collection and treatment device;

[0044] S3322. Calculate the abnormal impact of each component using a matrix algorithm based on the abnormal operation data;

[0045] S3323. Sort all components in the inorganic salt collection and treatment equipment according to the degree of abnormal impact of each component to obtain a sorting result.

[0046] According to another aspect of the present invention, there is provided an inorganic salt collection and processing monitoring device based on digital twin technology, the inorganic salt collection and processing monitoring device based on digital twin technology comprising: a model building module, a data acquisition module, an abnormality analysis module and a report generation module;

[0047] A model building module is used to build a digital twin simulation model based on parameter information of inorganic salt collection and processing equipment;

[0048] A data acquisition module is used to obtain real-time operation data of inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model;

[0049] The abnormality analysis module is used to analyze the abnormalities of inorganic salt collection and treatment equipment based on real-time operation data and simulation prediction data using extreme value theory and graph theory algorithms;

[0050] The report generation module is used to generate an abnormal analysis report based on the abnormal analysis results of the inorganic salt collection and treatment equipment.

[0051] The beneficial effects of the present invention are:

[0052] 1. By constructing a digital twin simulation model of the equipment, the present invention can achieve high-precision simulation of equipment performance and behavior, predict the performance of the equipment under different working conditions, help understand the response of the equipment under specific conditions, and accurately evaluate the difference between the actual performance of the equipment and the expected performance by comparing the real-time operation data with the simulation prediction data, so as to timely discover potential problems. The application of extreme value theory and graph theory algorithms to perform abnormal analysis on the equipment can effectively identify extreme behaviors or abnormal patterns in the operation of the equipment, extract key information from complex data, and quickly locate the source of the problem. Through continuous comparative analysis of real-time data and simulation data, preventive maintenance can be implemented, which can avoid equipment failures and production interruptions, help to achieve continuous optimization of equipment, improve production efficiency and reliability, while reducing operating costs and risks, and laying a solid foundation for the sustainable development of the enterprise.

[0053] 2. The present invention determines the deviation threshold by using extreme value theory, especially the Hill graph method, which can more accurately identify extreme values ​​in the data and effectively extract key threshold information from historical data. Constructing dependency relationships and equipment status diagrams not only helps to understand the interactions between components, but also can take these interactions into account during the analysis process to ensure the comprehensiveness and accuracy of abnormal analysis. Combining real-time operation data with simulation prediction data for analysis can more comprehensively identify and locate abnormalities, and utilizes the core advantage of digital twin technology, namely the ability to simulate and predict the behavior of equipment, so as to intervene before the abnormality occurs. By converting the equipment status diagram into an adjacency matrix and using a matrix algorithm to process abnormal data, the propagation path of the abnormality can be effectively tracked, thereby quickly locating the source of the fault.

[0054] 3. It is often extremely susceptible to the influence of other components, and this mutually influencing transmission path can be expressed by the edge weight in the device state diagram. By using the Dijkstra algorithm to determine the path between nodes and accumulate the edge weight values, a method of measuring the strength of the association between components is gradually accumulated. By randomly selecting node pairs in the device state diagram for path search multiple times, the comprehensiveness and balance of edge weights under different path combinations are ensured. By executing path search multiple times, the accuracy of weight calculation is further enhanced, so that the final generated adjacency matrix can better reflect the influence relationship between nodes in the device state diagram. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in 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. In the drawings:

[0056] Figure 1 is a flow chart of an inorganic salt collection, processing and monitoring method based on digital twin technology according to an embodiment of the present invention;

[0057] Figure 2 This is a principle block diagram of an inorganic salt collection, processing and monitoring device based on digital twin technology according to an embodiment of the present invention;

[0058] Figure 3 is a simplified schematic diagram of a device state diagram according to an embodiment of the present invention.

[0059] In the figure:

[0060] 1. Model building module; 2. Data acquisition module; 3. Abnormal analysis module; 4. Report generation module. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0062] According to an embodiment of the present invention, a method and device for monitoring the collection and processing of inorganic salts based on digital twin technology are provided.

[0063] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a method for monitoring the collection and processing of inorganic salts based on digital twin technology is provided, and the method for monitoring the collection and processing of inorganic salts based on digital twin technology comprises the following steps:

[0064] S1. Construct a digital twin simulation model based on the parameter information of the inorganic salt collection and processing equipment;

[0065] Specifically, according to the parameter information of the inorganic salt collection and processing equipment, building a digital twin simulation model includes the following steps:

[0066] Collect parameter information of inorganic salt collection and processing equipment, including equipment physical parameters, operating parameters, process parameters, control system parameters, environmental parameters, maintenance parameters, etc.

[0067] Integrate the collected parameter information into the digital twin platform and set parameters such as temperature, pressure, flow rate, etc. according to the actual operating conditions. Simulate the behavior of control systems and sensors to ensure that their interactions are consistent with reality.

[0068] After the model is built, it is verified and calibrated to ensure that the output of the model is consistent with the historical data and operating performance of the actual equipment. This includes: historical data comparison, comparing the output of the model with the actual data collected in the past to check for differences. Parameter fine-tuning, adjusting certain parameters in the model based on the comparison results to more accurately reflect the actual situation.

[0069] S2. Obtaining real-time operation data of inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model;

[0070] Specifically, obtaining the real-time operation data of the inorganic salt collection and treatment equipment and the simulation prediction data of the digital twin simulation model includes the following steps:

[0071] Use sensors pre-installed on the inorganic salt collection and treatment equipment, such as temperature sensors, pressure sensors, flow sensors, etc., to monitor various operating parameters of the equipment;

[0072] Establish a data acquisition system (such as a SCADA system or an IoT platform) to automatically collect real-time data sent by sensors;

[0073] Collect sensor data to a central server or cloud platform via wired or wireless means, and set up appropriate data storage mechanisms for subsequent analysis and processing;

[0074] Run simulations using the previously constructed digital twin simulation model; input initial and boundary conditions corresponding to real-time operation data;

[0075] Set simulation time step, simulation duration and other parameters as needed to ensure that simulation parameters match actual operating conditions to obtain accurate prediction results;

[0076] Run the simulation model, generate simulation prediction data, and monitor the simulation process to ensure that no anomalies or errors occur;

[0077] Export the simulation prediction data to an analyzable format such as CSV, Excel, etc., ensuring that the simulation prediction data contains timestamps and parameter values ​​corresponding to the real-time running data.

[0078] S3. Based on real-time operation data and simulation prediction data, the extreme value theory method and graph theory algorithm are used to analyze the abnormality of the inorganic salt collection and treatment equipment;

[0079] As a preferred implementation, based on real-time operation data and simulation prediction data, using extreme value theory and graph theory algorithm to analyze the abnormality of inorganic salt collection and treatment equipment includes the following steps:

[0080] S31, collecting historical operation data of the inorganic salt collection and processing equipment, and using the extreme value theory method to determine the deviation threshold of each operation data of the inorganic salt collection and processing equipment;

[0081] As a preferred implementation, collecting historical operation data of the inorganic salt collection and treatment equipment and using the extreme value theory method to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment includes the following steps:

[0082] S311, preprocessing the historical operation data of the inorganic salt collection and processing equipment;

[0083] It should be noted that the pre-processing of the historical operation data of the inorganic salt collection and treatment equipment includes:

[0084] Data cleaning to remove duplicate, missing or outlier values ​​to ensure data accuracy and completeness.

[0085] Data conversion: If the original data is not numerical, it needs to be converted into a numerical format suitable for analysis.

[0086] Data standardization, normalize or standardize the data to eliminate the influence of dimension and order of magnitude.

[0087] S312, performing descriptive statistical analysis on the preprocessed historical operation data to obtain distribution characteristics of the historical operation data;

[0088] As a preferred implementation, performing descriptive statistical analysis on the preprocessed historical operation data to obtain the distribution characteristics of the historical operation data includes the following steps:

[0089] S3121. Calculate the descriptive statistics of the preprocessed historical operation data;

[0090] It should be noted that descriptive statistics include mean, median, mode, variance, standard deviation, etc.;

[0091] The mean (average) is the sum of all observations divided by the number of observations. It provides a measure of the central tendency of the data set.

[0092] Median: The value in the middle of all the observations sorted by size. If the number of observations is even, then the median is the average of the two middle numbers.

[0093] Mode: The value that occurs most frequently in a data set. A data set may have one or more modes, or it may have no mode.

[0094] Variance: A measure of how dispersed the data points are relative to their mean. The larger the variance, the more dispersed the data points are.

[0095] Standard deviation: The square root of the variance, which is also a measure of the dispersion of data points, but has the same units as the original data.

[0096] S3122. Establish a histogram of the preprocessed historical operating data based on descriptive statistics, and calculate the skewness and kurtosis of the operating data;

[0097] It should be noted that a histogram is a commonly used graph used to display the distribution of continuous data. It displays data distribution by dividing the data into several intervals (called "bins" or "intervals") and drawing a histogram of the data frequency in each interval. The specific implementation steps are as follows:

[0098] Choose an appropriate number of bins based on the range of your data and the sample size. A common rule of thumb is the Sturges formula, which recommends the number of bins as:

[0099] h = 1 + 3.322log2 (m);

[0100] Where m is the number of samples.

[0101] The boundaries of each bin are determined based on the minimum and maximum values ​​of the data and the number of bins.

[0102] Traverse the data set, assign each data point to the corresponding bin, and count the number of data points in each bin.

[0103] Use statistical software or programming languages ​​(such as Python's matplotlib library) to draw a histogram, with the horizontal axis representing the range of data values ​​and the vertical axis representing the frequency or number.

[0104] In addition, skewness and kurtosis are two important statistics to measure the distribution shape of data, which describe the symmetry and sharpness of data distribution respectively. Skewness measures the symmetry of data distribution. If the skewness is 0, it means that the data distribution is symmetrical; if the skewness is positive, it means that the data distribution is right-skewed (long tail on the right); if the skewness is negative, it means that the data distribution is left-skewed (long tail on the left). Kurtosis measures the sharpness of data distribution. If the kurtosis is greater than 3, it means that the data distribution is sharper than the normal distribution (called peaked distribution); if the kurtosis is less than 3, it means that the data distribution is flatter than the normal distribution (called flat peaked distribution).

[0105] S3123. Analyze and interpret descriptive statistics, histograms, skewness and kurtosis to obtain the distribution characteristics of historical operating data.

[0106] It should be noted that the central tendency, dispersion, symmetry and sharpness of the data are analyzed by combining the histogram and statistics. For example, if the histogram shows that the data is right-skewed and the skewness is positive, this indicates that there are some large outliers in the data set. At the same time, if the kurtosis is greater than 3, the data may show a peak distribution, which means that most of the data is concentrated near the mean, while a few extreme values ​​are far away from the center.

[0107] S313. According to the distribution characteristics of the historical operation data, the Hill diagram method in the extreme value theory is used to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment.

[0108] It should be noted that the Hill graph method is a statistical method used in extreme value theory, mainly used to estimate the tail index, that is, the distribution characteristics of extreme values ​​in a large amount of data. The Hill estimator estimates the tail index based on the order statistics of the sample data. It focuses on the maximum value part of the data and tries to estimate the tail behavior in the data.

[0109] As a preferred implementation, according to the distribution characteristics of historical operation data, the Hill diagram method in extreme value theory is used to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment, including the following steps:

[0110] S3131, sorting the historical operation data in descending order, randomly selecting an initial threshold and calculating the Hill estimator;

[0111] It should be noted that a threshold is randomly selected, which will be used to filter out the "large" values ​​in the data set. These large values ​​will be used to calculate the Hill estimator. When selecting a threshold, the size of the data set and the expected proportion of extreme values ​​are generally considered.

[0112] As a preferred implementation, the formula for randomly selecting an initial threshold and calculating the Hill estimate is:

[0113]

[0114] In the formula, G k,n represents the Hill estimator;

[0115] k represents the number of data exceeding the initial threshold in the historical operation data;

[0116] n represents the number of historical operation data;

[0117] H(i) represents the i-th operation data in the historical operation data that exceeds the initial threshold;

[0118] H(k) represents the kth operation data in the historical operation data that exceeds the initial threshold.

[0119] S3132, establishing a Hill graph according to a randomly selected initial threshold and a Hill estimator;

[0120] It should be noted that the Hill diagram is drawn with the initial threshold or the number of observations exceeding the threshold as the horizontal axis and the corresponding Hill estimate as the vertical axis.

[0121] S3133. Perform a stationarity analysis on the established Hill graph, select the starting point of the stable interval in the Hill graph and use the starting point as the deviation threshold.

[0122] Specifically, in the Hill graph, the ideal situation is that the Hill estimator tends to stabilize as the number of observations increases, that is, the graph eventually tends to be horizontal. This means that the tail exponential estimate tends to be stable, which can relatively accurately reflect the tail characteristics of the data.

[0123] Observe the Hill graph and find the interval where the estimate begins to stabilize; this is usually manifested as a flat area in the graph, where the change in the estimate is no longer obvious and the fluctuation is small.

[0124] The starting point of this stable interval is selected as the deviation threshold. The choice of this threshold is based on the assumption that adding more data points will not significantly change the estimate of the tail index after this point, that is, the main characteristics of the tail of the data have been captured.

[0125] S32, analyzing the dependencies between the components in the inorganic salt collection and processing equipment, and constructing an equipment state diagram according to the dependencies;

[0126] As a preferred implementation, analyzing the dependencies between the components in the inorganic salt collection and processing equipment and constructing the equipment state diagram according to the dependencies includes the following steps:

[0127] S321. Collect the process flow of the inorganic salt collection and treatment equipment, and analyze the dependencies between the components in the inorganic salt collection and treatment equipment;

[0128] It should be noted that the process flow of inorganic salt collection and treatment equipment includes:

[0129] Raw material input, identifying the source, type and input method of the raw materials.

[0130] Main processing stages, such as dissolution, reaction, precipitation and other key processing steps.

[0131] Product output, product extraction, purification and packaging and other steps.

[0132] Waste disposal, how waste materials are handled and discharged.

[0133] Analyze the dependencies between the components in the inorganic salt collection and treatment equipment, including:

[0134] Identify the main functions of each component and its contribution to the process flow. For example, a pump is used to move liquids, and a reactor is used for chemical reactions.

[0135] Determine which operational steps rely on specific components functioning properly. For example, if a reactor needs to operate at specific temperatures and pressures, then the sensors and regulators that control these parameters are critical.

[0136] Analyze the physical and logical connections between components, such as fluid power connections, electrical signal transmission, etc.

[0137] S322, taking each component in the inorganic salt collection and processing equipment as a node, and taking the dependency relationship between the components as an edge;

[0138] It should be noted that by taking the components in the inorganic salt collection and treatment equipment as nodes and the dependencies between them as edges, an equipment state diagram can be effectively constructed, which helps to more clearly understand the structure and operation mechanism of the equipment.

[0139] S323. Construct a device status diagram between components based on the nodes and edges.

[0140] For example, suppose there is a simple inorganic salt treatment system consisting of a main reactor A, a circulation pump B, and a control valve C. The main reactor A relies on the circulation pump B to provide a constant flow of raw materials, while the control valve C regulates the product flow from the main reactor to the condenser. In the equipment state diagram, A, B, and C will be represented as nodes, and the relationship between A and B, and A and C will be represented by edges.

[0141] S33. Based on the real-time operation data and simulation prediction data, and according to the deviation threshold and the equipment status diagram, identify and locate the abnormality of the inorganic salt collection and processing equipment.

[0142] As a preferred embodiment, based on real-time operation data and simulation prediction data, and according to the deviation threshold and the equipment status diagram, identifying and locating the abnormality of the inorganic salt collection and treatment equipment includes the following steps:

[0143] S331, calculating the absolute value of the deviation between the real-time operation data and the simulation prediction data, and comparing the absolute value of the deviation with the deviation threshold to determine abnormal operation data;

[0144] It should be noted that for each pair of real-time data and simulated prediction data, a subtraction operation is performed to calculate the deviation value. Since the deviation may be positive or negative, its absolute value needs to be taken for unified comparison. The absolute value represents the non-directional difference between the data and the prediction value;

[0145] The deviation threshold is a predetermined limit used to determine whether the deviation between real-time data and simulated data is too large. This threshold should be determined based on the normal operating fluctuation range of the device and historical data. If the deviation value is greater than or equal to the deviation threshold, the corresponding real-time operating data is considered abnormal. If the deviation value is less than or equal to the deviation threshold, the corresponding real-time operating data is considered normal.

[0146] For example, suppose there is a set of real-time operation data and corresponding simulation prediction data:

[0147] Real-time operation data: R = {102, 98, 100, 105, 95};

[0148] Simulation prediction data: P = {100, 100, 100, 100, 100};

[0149] The deviation threshold is set to T=5.

[0150] Calculate the deviation value. For the real-time running data R and the simulation prediction data P, calculate the absolute value of the deviation value:

[0151] |102-100|=2;

[0152] |98-100|=2;

[0153] |100-100|=0;

[0154] |105-100|=5;

[0155] |95-100|=5;

[0156] The deviation value is compared with a deviation threshold value T=5.

[0157] Determine abnormal operating data:

[0158] The deviation values ​​of the real-time operation data 102 and 98 are both 2, which are both smaller than the deviation threshold value 5, and therefore they are normal.

[0159] The deviation value of the real-time operation data 100 is 0, which is smaller than the deviation threshold 5, and thus it is normal.

[0160] The deviation values ​​of the real-time operation data 105 and 95 are both 5, which is equal to the deviation threshold 5. According to the definition, these two data are considered abnormal.

[0161] That is to say, abnormal operation data refers to part of the real-time operation data with abnormal deviations.

[0162] S332. Identify abnormal operation data in the inorganic salt collection and processing equipment, and based on the equipment status diagram between the various components, identify and locate abnormal equipment in the inorganic salt collection and processing equipment through a matrix algorithm.

[0163] As a preferred embodiment, identifying abnormal operation data in the inorganic salt collection and treatment equipment, and based on the equipment status diagram between the components, identifying and locating abnormal equipment in the inorganic salt collection and treatment equipment through a matrix algorithm includes the following steps:

[0164] S3321, converting the device state diagram between the components into an adjacency matrix, wherein the rows and columns in the adjacency matrix represent different components in the inorganic salt collection and treatment device;

[0165] It should be noted that the device state diagram is a directed graph, where nodes represent the various components of the device and directed edges represent the dependency of one component on another. For example, if a pump requires an electric controller to drive it, there will be a directed edge from the electric controller to the pump.

[0166] The adjacency matrix is ​​a square matrix whose rows and columns represent the components of the device.

[0167] The element value a in the adjacency matrix rj Indicates: If component r has a direct impact or dependency on component j, then a in the matrix rj The element (row r, column j) is 1; if there is no direct influence or dependency, it is 0. That is, if there is a directed edge from node r to node j in the device state graph, then a rj is 1 if the value is true, otherwise it is 0.

[0168] S3322. Calculate the abnormal impact of each component using a matrix algorithm based on the abnormal operation data;

[0169] Specifically, based on the abnormal operation data in the inorganic salt collection and treatment equipment, calculating the degree of abnormal influence between components through matrix algorithm is an efficient method to diagnose and understand the propagation of problems. The specific implementation steps are as follows:

[0170] Integrate the real-time operating data of each component and the corresponding abnormal indicators, such as temperature, pressure or flow, which indicate the current operating status of each component. Standardize or convert these data into scores or indicators to quantify the degree of abnormality.

[0171] It should be noted here that since the abnormal operation data is essentially the data of each sensor device, it is necessary to convert the abnormal operation data corresponding to the sensor into the abnormal data vector corresponding to the device component, as shown in the following formula:

[0172]

[0173] Among them, F[j] represents the abnormal data of the jth device, k(i) represents the abnormal operation data corresponding to the i-th sensor, and m jrepresents the total number of sensors associated with the j-th device, and ε(i) represents the weight constant of the abnormal index corresponding to the i-th sensor.

[0174] You can refer to Figure 3 Understanding the above formula, the sensors corresponding to component F2 can be k4 and k5, and the total number of its associated sensors is 2.

[0175] The abnormal device vector is obtained by multiplying the adjacency matrix with the abnormal data vector. In this way, the impact of the abnormality can be propagated to the entire device through the dependency path, where each element in the abnormal device vector represents the degree of abnormal impact of the device (or component);

[0176] Update the weights in the adjacency matrix to reflect the actual impact. For example, if the original adjacency matrix uses binary (0 or 1), it may need to be adjusted to a weight value adjusted for the size of the abnormal data;

[0177] In some embodiments, the weight values ​​of the elements in the adjacency matrix may be calculated based on the principle of maximum flow, which specifically includes steps S401 to S403.

[0178] Step S401: randomly select any two nodes in the device state graph, use the Dijkstra algorithm to determine the path between the two nodes, and add 1 to the weight value of the edge involved in the path.

[0179] Step S402: Use different random seeds and execute step S401 multiple times.

[0180] In some embodiments, multiple executions means that the number of executions should be more than 5 times the square of the number of nodes in the device state graph.

[0181] Step S403: Use the weights in the final device state graph as the weights of the corresponding elements in the adjacency matrix.

[0182] Once the calculation is complete, each element value in the result matrix will represent the degree of influence of one component on another. High values ​​indicate a large degree of influence, which can help determine which components may be the source of the failure or the most affected component.

[0183] S3323. Sort all components in the inorganic salt collection and treatment equipment according to the degree of abnormal impact of each component to obtain a sorting result.

[0184] Specifically, sorting all components in the inorganic salt collection and treatment equipment according to the degree of abnormal impact can help prioritize those components that have the greatest impact on the entire system, thereby more effectively performing fault diagnosis and maintenance. The specific implementation steps are as follows:

[0185] For each component, the total score of its impact on other components can be obtained by summing up each column in the impact matrix, because the value of each column represents the sum of the impact of the component corresponding to the column on all other components.

[0186] Rank the components according to the total impact score calculated in the previous step. Components with higher scores have a greater impact on the entire equipment and should be given priority for inspection and maintenance.

[0187] S4. Generate an abnormal analysis report based on the abnormal analysis results of the inorganic salt collection and treatment equipment.

[0188] Specifically, the abnormal analysis report of inorganic salt collection and treatment equipment should record the entire process from abnormal discovery to analysis, including the report overview, abnormal identification, data analysis, abnormal impact analysis, fault location, recommended measures and summary. The report should describe in detail how to identify abnormalities through real-time monitoring and simulation data, calculate and sort the impact of each component through adjacency matrix and data analysis, and how to identify key components and make specific maintenance and operation suggestions. In addition, the report should also include relevant data charts and technical documents to ensure that all relevant personnel can understand the problem and take prompt action to improve the stability and production efficiency of the equipment.

[0189] like Figure 2 As shown, according to another embodiment of the present invention, an inorganic salt collection and processing monitoring device based on digital twin technology is provided, and the inorganic salt collection and processing monitoring device based on digital twin technology includes: a model building module 1, a data acquisition module 2, an abnormality analysis module 3 and a report generation module 4;

[0190] Model building module 1, used to build a digital twin simulation model based on parameter information of inorganic salt collection and processing equipment;

[0191] Data acquisition module 2, used to obtain real-time operation data of inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model;

[0192] Abnormal analysis module 3, used to analyze abnormalities of inorganic salt collection and treatment equipment based on real-time operation data and simulation prediction data using extreme value theory and graph theory algorithms;

[0193] The report generation module 4 is used to generate an abnormality analysis report according to the abnormality analysis results of the inorganic salt collection and treatment equipment.

[0194] In summary, with the help of the above-mentioned technical scheme of the present invention, the present invention can achieve high-precision simulation of equipment performance and behavior by constructing a digital twin simulation model of the equipment, can predict the performance of the equipment under different working conditions, and help understand the response of the equipment under specific conditions. By comparing real-time operation data with simulation prediction data, the difference between the actual performance and the expected performance of the equipment can be accurately evaluated, so as to timely discover potential problems. The application of extreme value theory and graph theory algorithms to perform abnormal analysis on the equipment can effectively identify extreme behaviors or abnormal patterns in equipment operation, can extract key information from complex data, and quickly locate the source of the problem. Through continuous comparative analysis of real-time data and simulation data, preventive maintenance can be implemented, which can avoid equipment failures and production interruptions, help to achieve continuous optimization of equipment, improve production efficiency and reliability, while reducing operating costs and risks, and laying a solid foundation for the sustainable development of the enterprise. The present invention determines the deviation threshold by using extreme value theory, especially the Hill graph method, which can more accurately identify extreme values ​​in the data and effectively extract key threshold information from historical data. Constructing dependency relationships and device status diagrams not only helps to understand the interactions between components, but also can take these interactions into account during the analysis process to ensure the comprehensiveness and accuracy of abnormality analysis. Combining real-time operation data with simulation prediction data for analysis can more comprehensively identify and locate abnormalities. It utilizes the core advantage of digital twin technology, namely the ability to simulate and predict the behavior of equipment, so as to intervene before the abnormality occurs. By converting the device state diagram into an adjacency matrix and using a matrix algorithm to process abnormal data, the propagation path of the abnormality can be effectively tracked, thereby quickly locating the source of the fault.

[0195] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0196] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring the collection and processing of inorganic salts based on digital twin technology, characterized in that: The inorganic salt collection and processing monitoring method based on digital twin technology includes the following steps: S1. Construct a digital twin simulation model based on the parameter information of the inorganic salt collection and processing equipment; S2. Obtaining real-time operation data of inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model; S3. Based on real-time operation data and simulation prediction data, the extreme value theory method and graph theory algorithm are used to analyze the abnormality of the inorganic salt collection and treatment equipment; S4. Generate an abnormal analysis report based on the abnormal analysis results of the inorganic salt collection and treatment equipment.

2. According to claim 1, a method for monitoring the collection and treatment of inorganic salts based on digital twin technology is characterized in that: The analysis of the abnormality of the inorganic salt collection and treatment equipment based on the real-time operation data and the simulation prediction data using the extreme value theory method and the graph theory algorithm includes the following steps: S31, collecting historical operation data of the inorganic salt collection and processing equipment, and using the extreme value theory method to determine the deviation threshold of each operation data of the inorganic salt collection and processing equipment; S32, analyzing the dependencies between the components in the inorganic salt collection and processing equipment, and constructing an equipment state diagram according to the dependencies; S33. Based on the real-time operation data and simulation prediction data, and according to the deviation threshold and the equipment status diagram, identify and locate the abnormality of the inorganic salt collection and processing equipment.

3. According to claim 2, a method for monitoring the collection, processing and use of inorganic salts based on digital twin technology is characterized in that: The method of collecting historical operation data of the inorganic salt collection and treatment equipment and determining the deviation threshold of each operation data of the inorganic salt collection and treatment equipment by using the extreme value theory method comprises the following steps: S311, preprocessing the historical operation data of the inorganic salt collection and processing equipment; S312, performing descriptive statistical analysis on the preprocessed historical operation data to obtain distribution characteristics of the historical operation data; S313. According to the distribution characteristics of the historical operation data, the Hill diagram method in the extreme value theory is used to determine the deviation threshold of each operation data of the inorganic salt collection and treatment equipment.

4. According to claim 3, a method for monitoring the collection, processing and use of inorganic salts based on digital twin technology is characterized in that: The performing of descriptive statistical analysis on the preprocessed historical operation data to obtain the distribution characteristics of the historical operation data comprises the following steps: S3121. Calculate the descriptive statistics of the preprocessed historical operation data; S3122. Establish a histogram of the preprocessed historical operating data based on descriptive statistics, and calculate the skewness and kurtosis of the operating data; S3123. Analyze and interpret descriptive statistics, histograms, skewness and kurtosis to obtain the distribution characteristics of historical operating data.

5. The method for monitoring the collection and treatment of inorganic salts based on digital twin technology according to claim 3, characterized in that: The method of determining the deviation threshold of each operation data of the inorganic salt collection and treatment equipment by using the Hill diagram method in extreme value theory according to the distribution characteristics of the historical operation data comprises the following steps: S3131, sorting the historical operation data in descending order, randomly selecting an initial threshold and calculating the Hill estimator; S3132, establishing a Hill graph according to a randomly selected initial threshold and a Hill estimator; S3133. Perform a stationarity analysis on the established Hill graph, select the starting point of the stable interval in the Hill graph and use the starting point as the deviation threshold.

6. The method for monitoring the collection and treatment of inorganic salts based on digital twin technology according to claim 5, characterized in that: The formula for randomly selecting an initial threshold and calculating the Hill estimator is: In the formula, G k,n represents the Hill estimator; k represents the number of data exceeding the initial threshold in the historical operation data; n represents the number of historical operation data; H(i) represents the i-th operation data in the historical operation data that exceeds the initial threshold; H(k) represents the kth operation data in the historical operation data that exceeds the initial threshold.

7. The method for monitoring the collection, processing and use of inorganic salts based on digital twin technology according to claim 2, characterized in that: The analysis of the dependency relationship between the components in the inorganic salt collection and treatment equipment and the construction of the equipment state diagram according to the dependency relationship include the following steps: S321. Collect the process flow of the inorganic salt collection and treatment equipment, and analyze the dependencies between the components in the inorganic salt collection and treatment equipment; S322, taking each component in the inorganic salt collection and processing equipment as a node, and taking the dependency relationship between the components as an edge; S323. Construct a device status diagram between components based on the nodes and edges.

8. The method for monitoring the collection and treatment of inorganic salts based on digital twin technology according to claim 2, characterized in that: The method of identifying and locating anomalies of inorganic salt collection and treatment equipment based on real-time operation data and simulation prediction data and according to deviation thresholds and equipment status diagrams includes the following steps: S331, calculating the absolute value of the deviation between the real-time operation data and the simulation prediction data, and comparing the absolute value of the deviation with the deviation threshold to determine abnormal operation data; S332. Identify abnormal operation data in the inorganic salt collection and processing equipment, and based on the equipment status diagram between the various components, identify and locate abnormal equipment in the inorganic salt collection and processing equipment through a matrix algorithm.

9. The method for monitoring the collection, processing and use of inorganic salts based on digital twin technology according to claim 8, characterized in that: The method of identifying abnormal operation data in the inorganic salt collection and treatment equipment and identifying and locating abnormal equipment in the inorganic salt collection and treatment equipment through a matrix algorithm based on the equipment status diagram between the components includes the following steps: S3321, converting the device state diagram between the components into an adjacency matrix, wherein the rows and columns in the adjacency matrix represent different components in the inorganic salt collection and treatment device; S3322. Calculate the abnormal impact of each component using a matrix algorithm based on the abnormal operation data; S3323. Sort all components in the inorganic salt collection and treatment equipment according to the degree of abnormal impact of each component to obtain a sorting result.

10. An inorganic salt collection and processing monitoring device based on digital twin technology, used to implement the inorganic salt collection and processing monitoring method based on digital twin technology according to any one of claims 1 to 9, characterized in that: The inorganic salt collection and processing monitoring device based on digital twin technology includes: a model building module, a data acquisition module, an abnormality analysis module and a report generation module; The model building module is used to build a digital twin simulation model according to parameter information of the inorganic salt collection and processing equipment; The data acquisition module is used to obtain real-time operation data of the inorganic salt collection and processing equipment and simulation prediction data of the digital twin simulation model; The abnormality analysis module is used to analyze the abnormality of the inorganic salt collection and treatment equipment based on real-time operation data and simulation prediction data using extreme value theory and graph theory algorithms; The report generating module is used to generate an abnormality analysis report according to the abnormality analysis result of the inorganic salt collecting and processing equipment.

Images