Production fluctuation early warning model acquisition method and device, equipment and storage medium

Abstract

The invention discloses a production fluctuation early warning model obtaining method and device, equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring historical data of each process parameter of the refining device, wherein the historical data of any process parameter comprises a first numerical value of any process parameter at each historical time and a credible value of the first numerical value; determining key process parameters in the process parameters, wherein the key process parameters are process parameters influencing the production fluctuation of the refining device; according to the credible value of the first numerical value of the key process parameter in each historical time, processing the first numerical value of the key process parameter in each historical time to obtain a second numerical value of the key process parameter in each historical time; and obtaining a production fluctuation early warning model corresponding to the key process parameter according to the second numerical value of the key process parameter at each historical time. According to the method, the production efficiency and safety of the refining device are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for obtaining a production fluctuation early warning model. Background Technology

[0002] Production fluctuations in refining and chemical plants refer to the process of collecting and analyzing data on process parameters in the refining and chemical production process to determine which process parameters caused the production fluctuations, and then identifying the equipment corresponding to those process parameters so as to take appropriate measures to avoid or mitigate the impact on the production of the refining and chemical plants.

[0003] In related technologies, when a process parameter in a refining unit experiences production fluctuations, the corresponding equipment is manually adjusted based on experience. This method is easily influenced by the experience and subjective judgment of technicians, and the equipment's response is often delayed, leading to lower production efficiency and safety in the refining unit. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for acquiring a production fluctuation early warning model, which can be used to solve problems in related technologies. The technical solution is as follows:

[0005] On one hand, embodiments of this application provide a method for obtaining a production fluctuation early warning model, the method comprising:

[0006] Historical data of various process parameters of the refining and chemical unit are obtained. The historical data of any process parameter includes the first value of the process parameter at each historical time and the confidence value of the first value.

[0007] Among the various process parameters, key process parameters are identified, which are the process parameters that affect the production fluctuations of the refining and chemical unit.

[0008] Based on the confidence value of the first value of the key process parameter at each historical time, the first value of the key process parameter at each historical time is processed to obtain the second value of the key process parameter at each historical time.

[0009] Based on the second values ​​of the key process parameters at each historical time, a production fluctuation early warning model corresponding to the key process parameters is obtained. The production fluctuation early warning model corresponding to the key process parameters is used to predict the values ​​of the key process parameters at a target time. The target time is later than each historical time and adjacent to the latest time among each historical time.

[0010] In one possible implementation, determining the key process parameters among the various process parameters includes:

[0011] Based on the first values ​​of each process parameter at each historical time, the correlation coefficient between any two process parameters is determined, and the correlation coefficient between any two process parameters is used to indicate the correlation relationship between the two process parameters.

[0012] Based on the correlation coefficient between any two process parameters, the key process parameters are determined among the various process parameters.

[0013] In one possible implementation, determining the key process parameter among the various process parameters based on the correlation coefficient between any two process parameters includes:

[0014] Based on the correlation coefficient between any two process parameters, the coefficient of each process parameter is determined, and the coefficient of any process parameter is used to indicate the degree of influence of any process parameter on the production fluctuation of the refining and chemical unit.

[0015] Based on the coefficients of each process parameter, the process parameters are sorted according to the target order to obtain the sorting result;

[0016] The process parameters that meet the sorting requirements in the sorting results are identified as the key process parameters.

[0017] In one possible implementation, determining the coefficients of each process parameter based on the correlation coefficient between any two process parameters includes:

[0018] For any process parameter among the various process parameters, at least one target correlation coefficient is determined from the correlation coefficients between any two process parameters. Any target correlation coefficient is the correlation coefficient between any process parameter and a reference process parameter. The reference process parameter is the process parameter other than any process parameter among the various process parameters.

[0019] The average value of the at least one target correlation coefficient is determined to be the coefficient of any one of the process parameters.

[0020] In one possible implementation, processing the first value of the key process parameter at each historical time based on the confidence value of the first value of the key process parameter at each historical time to obtain the second value of the key process parameter at each historical time includes:

[0021] If the confidence value of the first value of the key process parameter at each historical time is not less than the confidence threshold, the first value of the key process parameter at each historical time is determined as the second value of the key process parameter at each historical time.

[0022] If the confidence value of the first value of the key process parameter at the first historical time is less than the confidence threshold, a function corresponding to the key process parameter is generated based on the first value of the key process parameter at the second historical time; and a second value of the key process parameter at the first historical time is determined based on the function corresponding to the key process parameter and the first historical time.

[0023] The second historical time refers to the historical time other than the first historical time among the various historical times.

[0024] In one possible implementation, obtaining the production fluctuation early warning model corresponding to the key process parameter based on its second value at various historical times includes:

[0025] Input each historical time into the initial model to obtain the first predicted value corresponding to each historical time;

[0026] The first loss value is determined based on the first predicted value corresponding to each historical time and the second value of the key process parameter at each historical time.

[0027] If the first loss value is not lower than the loss threshold, the model parameters of the initial model are adjusted to obtain the adjusted model;

[0028] The historical time is input into the adjustment model to obtain the second predicted value corresponding to each historical time.

[0029] The second loss value is determined based on the second predicted value corresponding to each historical time and the second value of the key process parameter at each historical time.

[0030] If the second loss value is lower than the loss threshold, the adjustment model is determined to be the production fluctuation early warning model corresponding to the key process parameter.

[0031] In one possible implementation, after obtaining the production fluctuation early warning model corresponding to the key process parameter based on the second value of the key process parameter at various historical times, the method further includes:

[0032] The target time is input into the production fluctuation early warning model corresponding to the key process parameter to obtain the value of the key process parameter at the target time.

[0033] In one possible implementation, the method further includes:

[0034] Based on the second values ​​of the key process parameters at each historical time and the values ​​of the key process parameters at the target time, a fluctuation curve of the key process parameters is generated.

[0035] If, based on the fluctuation curve, it is determined that the key process parameter has experienced production fluctuations, an early warning is issued according to the target early warning method. The production fluctuation of the key process parameter includes an anomaly in the reference portion of the fluctuation curve, where the reference portion is the part between the latest time in the historical time and the target time.

[0036] In one possible implementation, the reference portion exception includes:

[0037] The trend of the reference portion is different from the trend of the portion of the fluctuation curve other than the reference portion.

[0038] In one possible implementation, the early warning according to the target early warning method includes at least one of the following:

[0039] Display a notification message, which indicates that the key process parameter has become abnormal;

[0040] Send the notification message to the terminal device corresponding to the managed object;

[0041] Play voice data, which is used to indicate that the key process parameters are abnormal.

[0042] On the other hand, embodiments of this application provide an apparatus for acquiring a production fluctuation early warning model, the apparatus comprising:

[0043] The acquisition module is used to acquire historical data of various process parameters of the refining and chemical unit. The historical data of any process parameter includes the first value of the process parameter at each historical time and the confidence value of the first value.

[0044] A determination module is used to determine key process parameters among the various process parameters, wherein the key process parameters are process parameters that affect the production fluctuations of the refining and chemical unit;

[0045] The processing module is used to process the first value of the key process parameter at each historical time according to the confidence value of the first value of the key process parameter at each historical time, so as to obtain the second value of the key process parameter at each historical time.

[0046] The acquisition module is further configured to acquire a production fluctuation early warning model corresponding to the key process parameter based on the second values ​​of the key process parameter at each historical time. The production fluctuation early warning model corresponding to the key process parameter is used to predict the value of the key process parameter at a target time. The target time is later than each historical time and adjacent to the latest time among each historical time.

[0047] In one possible implementation, the determining module is configured to determine the correlation coefficient between any two process parameters based on the first values ​​of each process parameter at each historical time, wherein the correlation coefficient between any two process parameters is used to indicate the correlation between the two process parameters; and to determine the key process parameter among the process parameters based on the correlation coefficient between the two process parameters.

[0048] In one possible implementation, the determining module is configured to determine the coefficients of each process parameter based on the correlation coefficient between any two process parameters, wherein the coefficient of any process parameter is used to indicate the degree of influence of any process parameter on the production fluctuation of the refining and chemical unit; sort the process parameters according to the target order based on the coefficients of each process parameter to obtain a sorting result; and determine the process parameters that meet the sorting requirements in the sorting result as the key process parameters.

[0049] In one possible implementation, the determining module is configured to, for any process parameter among the various process parameters, determine at least one target correlation coefficient among the correlation coefficients between any two process parameters, wherein any target correlation coefficient is the correlation coefficient between any process parameter and a reference process parameter, and the reference process parameter is the process parameter other than the any process parameter among the various process parameters; and determine the average value of the at least one target correlation coefficient as the coefficient of the any process parameter.

[0050] In one possible implementation, the processing module is configured to: determine the first value of the key process parameter at each historical time as a second value of the key process parameter at each historical time, provided that the confidence value of the first value of the key process parameter at each historical time is not less than a confidence threshold; generate a function corresponding to the key process parameter based on the first value of the key process parameter at the second historical time, provided that the confidence value of the first value of the key process parameter at the first historical time is less than the confidence threshold; and determine the second value of the key process parameter at the first historical time based on the function corresponding to the key process parameter and the first historical time; wherein the second historical time is a historical time other than the first historical time among the various historical times.

[0051] In one possible implementation, the acquisition module is configured to input the various historical times into an initial model to obtain a first predicted value corresponding to each historical time; determine a first loss value based on the first predicted value corresponding to each historical time and a second value of the key process parameter at each historical time; adjust the model parameters of the initial model to obtain an adjusted model if the first loss value is not lower than a loss threshold; input the various historical times into the adjusted model to obtain a second predicted value corresponding to each historical time; determine a second loss value based on the second predicted value corresponding to each historical time and a second value of the key process parameter at each historical time; and determine the adjusted model as a production fluctuation early warning model corresponding to the key process parameter if the second loss value is lower than the loss threshold.

[0052] In one possible implementation, the determining module is further configured to input the target time into the production fluctuation early warning model corresponding to the key process parameter, and obtain the value of the key process parameter at the target time.

[0053] In one possible implementation, the device further includes:

[0054] The generation module is used to generate the fluctuation curve of the key process parameter based on the second value of the key process parameter at each historical time and the value of the key process parameter at the target time.

[0055] The early warning module is used to issue an early warning according to a target early warning method when it is determined that the key process parameter has experienced production fluctuations based on the fluctuation curve. The production fluctuations of the key process parameter include anomalies in the reference portion of the fluctuation curve, where the reference portion is the part between the latest time in the historical time and the target time.

[0056] In one possible implementation, the reference portion exception includes:

[0057] The trend of the reference portion is different from the trend of the portion of the fluctuation curve other than the reference portion.

[0058] In one possible implementation, the early warning module is configured to perform at least one of the following: display a notification message indicating that the key process parameter is abnormal; send the notification message to the terminal device corresponding to the managed object; and play voice data indicating that the key process parameter is abnormal.

[0059] On the other hand, embodiments of this application provide a computer device, the computer device including a processor and a memory, the memory storing at least one piece of program code, the at least one piece of program code being loaded and executed by the processor, so that the computer device implements the method for obtaining the production fluctuation early warning model described above.

[0060] On the other hand, a computer-readable storage medium is also provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to enable a computer to implement the method for obtaining the production fluctuation early warning model as described above.

[0061] On the other hand, a computer program or computer program product is also provided, wherein the computer program or computer program product stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement any of the above-mentioned methods for obtaining production fluctuation early warning models.

[0062] The technical solution provided in this application has at least the following beneficial effects:

[0063] The technical solution provided in this application identifies key process parameters affecting production fluctuations in a refining and chemical plant. Based on historical data of these key process parameters, a corresponding production fluctuation early warning model is obtained. This model is then used to predict the value of the key process parameter at a target time. The value of the key process parameter at the target time determines whether a production fluctuation has occurred. If a production fluctuation is imminent, a timely warning is issued and addressed. This allows for rapid identification of potential production fluctuations and provides sufficient time for technicians to resolve the issue before a failure occurs. Furthermore, more precise monitoring and timely warnings reduce the number of production interruptions in the refining and chemical plant, improving its production efficiency. In addition, since production fluctuations can potentially lead to safety hazards such as equipment damage and environmental pollution, real-time monitoring and early warnings help to promptly identify and address potential safety issues, thereby improving the safety of the production process. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1This is a schematic diagram of the implementation environment for a method for obtaining a production fluctuation early warning model provided in an embodiment of this application;

[0066] Figure 2 This is a flowchart of a method for obtaining a production fluctuation early warning model provided in an embodiment of this application;

[0067] Figure 3 This is a schematic diagram illustrating the process of determining a production fluctuation model corresponding to a key process parameter provided in an embodiment of this application;

[0068] Figure 4 This is a flowchart illustrating the usage of a production fluctuation early warning model corresponding to a key process parameter provided in this application embodiment;

[0069] Figure 5 This is a schematic diagram of the structure of a device for acquiring a production fluctuation early warning model provided in an embodiment of this application;

[0070] Figure 6 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0071] Figure 7 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0073] It should be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0074] Figure 1 This is a schematic diagram illustrating the implementation environment of a method for obtaining a production fluctuation early warning model provided in this application embodiment, such as... Figure 1 As shown, the implementation environment includes a computer device 101, which can be a terminal device or a server; this embodiment does not limit the specific type of device. The computer device 101 is used to execute the method for obtaining the production fluctuation early warning model provided in this embodiment.

[0075] Optionally, computer device 101 is a terminal device. A terminal device can be any electronic device that allows human-computer interaction with a user through one or more methods such as a keyboard, touchpad, remote control, voice interaction, or handwriting device. Examples include PCs (Personal Computers), mobile phones, smartphones, PDAs (Personal Digital Assistants), wearable devices, PPCs (Pocket PCs), tablets, smart car systems, smart TVs, smart speakers, and smartwatches.

[0076] A terminal device can refer to one of multiple terminal devices; this embodiment uses only one terminal device as an example. Those skilled in the art will understand that the number of terminal devices can be more or less. For example, there may be only one terminal device, or there may be dozens or hundreds, or even more. This application embodiment does not limit the number or type of terminal devices.

[0077] When computer device 101 is a server, the server can be a single server, a server cluster consisting of multiple servers, or any of the following: a cloud computing platform or a virtualization center. This application embodiment does not limit this. The server and terminal devices communicate via a wired or wireless network. The server has data receiving, data processing, and data sending functions. Of course, the server may also have other functions, which this application embodiment does not limit.

[0078] Those skilled in the art should understand that the above-described terminal devices and servers are merely illustrative examples. Other existing or future terminal devices or servers that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0079] This application provides a method for obtaining a production fluctuation early warning model, which can be applied to the above-mentioned... Figure 1 The implementation environment shown is as follows: Figure 2 The flowchart shown in this embodiment of the present application illustrates a method for obtaining a production fluctuation early warning model. This method can be implemented by... Figure 1 The computer device 101 in the middle performs the operation. For example... Figure 2 As shown, the method includes the following steps 201 to 204.

[0080] In step 201, historical data of each process parameter of the refining unit is obtained. The historical data of any process parameter includes the first value of the process parameter at each historical time and the confidence value of the first value.

[0081] In the exemplary embodiments of this application, the number of process parameters of the refining unit is at least one. The process parameters of different refining units may be the same or different, and this application embodiment does not limit this. For example, taking an atmospheric and vacuum distillation unit as an example, the process parameters of the refining unit include, but are not limited to, the inlet temperature of the cracking section, the cold feed rate, the hot feed rate, the top temperature of the tower, the separator pressure, and the outlet temperature of the atmospheric furnace.

[0082] Each process parameter in the refining unit corresponds to a set of historical data. The historical data for any given process parameter includes its first value at each historical time and its reliability value. The reliability value indicates the degree of trustworthiness of the first value, and this reliability is directly proportional to the degree of trustworthiness. That is, the higher the reliability value of a first value, the higher its degree of trustworthiness, and vice versa. The number of historical data sets for each process parameter is the same.

[0083] Table 1 below is an exemplary table of historical data on the outlet temperature of the atmospheric furnace of a refining and chemical plant provided in the embodiments of this application.

[0084] Table 1

[0085]

[0086]

[0087] As shown in Table 1 above, the first value of the atmospheric pressure furnace outlet temperature at 12:34 on February 1, 2023 was 357.9, and the confidence value of the first value of the atmospheric pressure furnace outlet temperature at 12:34 on February 1, 2023 was 100. The first values ​​of the atmospheric pressure furnace outlet temperature at other times and their confidence values ​​are also shown in Table 1 above, and will not be repeated here in the embodiments of this application.

[0088] It should be noted that the historical data of other process parameters are similar to the historical data of the atmospheric pressure furnace outlet temperature, and will not be repeated here in the embodiments of this application.

[0089] It should also be noted that the historical data for any process parameter may include other content, and this application embodiment does not limit this.

[0090] In one possible implementation, after obtaining historical data of various process parameters of the refining unit, the historical data of these parameters can be stored in a big data platform for subsequent processing. This big data platform can be Hadoop (a distributed computing and storage framework), or other big data platforms; this application does not limit the specific implementation. Hadoop is a distributed system infrastructure that allows users to develop distributed programs without understanding the underlying details of distributed systems, fully utilizing the power of clusters for high-speed computation and storage. Hadoop implements a distributed file system, one component of which is HDFS (Hadoop Distributed File System). HDFS is highly fault-tolerant and designed for deployment on low-cost hardware; it also provides high throughput access to application data, making it suitable for applications with large datasets. HDFS relaxes POSIX (Portable Operating System Interface) requirements, allowing streaming access to data in the file system. The core design of the Hadoop framework consists of HDFS and MapReduce (a programming model). HDFS provides storage for massive amounts of data, while MapReduce provides computation for massive amounts of data.

[0091] In step 202, key process parameters are identified among the various process parameters. These key process parameters are those that affect the production fluctuations of the refining and chemical unit.

[0092] In one possible implementation, some process parameters of the refining and chemical unit do not affect the production fluctuations of the refining and chemical unit, while others do. Therefore, it is necessary to identify the key process parameters among the various process parameters of the refining and chemical unit. The key process parameters are those that affect the production fluctuations of the refining and chemical unit.

[0093] This application does not limit the process of determining key process parameters among various process parameters. Optionally, the process of determining key process parameters among various process parameters includes: determining the correlation coefficient between any two process parameters based on the first values ​​of each historical time for each process parameter, wherein the correlation coefficient between any two process parameters is used to indicate the correlation between the two process parameters; and determining the key process parameter among various process parameters based on the correlation coefficient between any two process parameters. The higher the correlation coefficient between any two process parameters, the stronger the correlation between the two process parameters; conversely, the lower the correlation coefficient between any two process parameters, the weaker the correlation between the two process parameters.

[0094] In one possible implementation, the correlation coefficient between any two process parameters is determined according to the first value of each process parameter at each historical time, using the following formula (1).

[0095]

[0096] In the above formula (1), r(x,y) is the correlation coefficient between process parameter x and process parameter y, cov(x,y) is the covariance between process parameter x and process parameter y, σx is the standard deviation of process parameter x, and σy is the standard deviation of process parameter y.

[0097] In one possible implementation, after determining the correlation coefficient between any two process parameters, the process of determining the key process parameters based on the correlation coefficient between any two process parameters includes: determining the coefficient of each process parameter based on the correlation coefficient between any two process parameters, wherein the coefficient of any process parameter is used to indicate the degree of influence of any process parameter on the production fluctuation of the refining and chemical unit; sorting each process parameter according to the target order based on the coefficient of each process parameter to obtain the sorting result; and determining the process parameters that meet the sorting requirements in the sorting result as key process parameters.

[0098] The coefficient of any process parameter is directly proportional to its influence on the production fluctuations of the refining unit. That is, the higher the coefficient of any process parameter, the greater its influence on the production fluctuations of the refining unit; conversely, the lower the coefficient, the smaller its influence. The target order is set based on experience or adjusted according to the implementation environment; this embodiment does not limit this. For example, the target order is either from smallest to largest or from largest to smallest. The process parameters that meet the sorting requirements in the sorting results are related to the target order. If the target order is from smallest to largest, then the process parameters that meet the sorting requirements in the sorting results are those after the target position. If the target order is from largest to smallest, then the process parameters that meet the sorting requirements in the sorting results are those before the target position. The target position is set based on experience or adjusted according to the implementation environment; this embodiment does not limit this. For example, the target position is the fourth position.

[0099] In one possible implementation, the process of determining the coefficients of each process parameter based on the correlation coefficient between any two process parameters includes: for any process parameter among the process parameters, determining at least one target correlation coefficient among the correlation coefficients between any two process parameters, wherein any target correlation coefficient is the correlation coefficient between any process parameter and a reference process parameter, and the reference process parameter is the process parameter other than any process parameter among the process parameters; and determining the average value of the at least one target correlation coefficient as the coefficient of any process parameter.

[0100] For example, the refining equipment has five process parameters: cracking section inlet temperature, cold feed rate, hot feed rate, tower top temperature, and separator pressure. The correlation coefficients between any two process parameters are shown in Table 2 below, and will not be elaborated further in this embodiment.

[0101] Table 2

[0102]

[0103] For the process parameter of cracking section inlet temperature, the process of determining its coefficient includes: identifying the correlation coefficients between the cracking section inlet temperature and other process parameters (excluding the cracking section inlet temperature) from the correlation coefficients between any two process parameters. Specifically, the target correlation coefficients are: 0.53 between the cracking section inlet temperature and the cold feed rate; 0.29 between the cracking section inlet temperature and the hot feed rate; 0.22 between the cracking section inlet temperature and the tower top temperature; and 0.46 between the cracking section inlet temperature and the separator pressure. The average value of the target correlation coefficients is (0.53 + 0.29 + 0.22 + 0.46) / 4 = 0.375. Therefore, the coefficient for the cracking section inlet temperature is 0.375.

[0104] Following the method used to determine the coefficient of the cracking section inlet temperature, the coefficients of other process parameters of the refining unit are determined. For example, the coefficient for cold feed rate is 0.325, the coefficient for hot feed rate is 0.29, the coefficient for tower top temperature is 0.1625, and the coefficient for separator pressure is 0.2925. The process parameters are then sorted in descending order of their coefficients, resulting in the following order: cracking section inlet temperature, cold feed rate, separator pressure, hot feed rate, and tower top temperature. The process parameters ranked before the fourth highest are considered critical process parameters; that is, the cracking section inlet temperature, cold feed rate, and separator pressure are designated as critical process parameters.

[0105] This application embodiment determines key process parameters among various process parameters of the refining and chemical unit, and then obtains a production fluctuation early warning model corresponding to each key process parameter of the refining and chemical unit. This enables each key process parameter of the refining and chemical unit to be monitored, allowing for more comprehensive monitoring of the production process of the refining and chemical unit and ensuring that no factors that may cause production fluctuations in the refining and chemical unit are overlooked.

[0106] In step 203, based on the reliability of the first values ​​of the key process parameters at each historical time, the first values ​​of the key process parameters at each historical time are processed to obtain the second values ​​of the key process parameters at each historical time.

[0107] The confidence threshold is set based on experience or adjusted according to the implementation environment; this application embodiment does not limit this. For example, the confidence threshold is 100.

[0108] Since the first values ​​of key process parameters at various historical times may contain values ​​with confidence values ​​lower than a confidence threshold, it is necessary to process these first values ​​to obtain second values ​​for each historical time. In one possible implementation, the process of processing the first values ​​of key process parameters at various historical times to obtain second values ​​includes: if the confidence values ​​of the first values ​​of key process parameters at each historical time are not less than the confidence threshold, then the first values ​​of key process parameters at each historical time are determined as the second values ​​for each historical time. If the confidence value of the first value of key process parameters at the first historical time is less than the confidence threshold, then a function corresponding to the key process parameter is generated based on the first value of the key process parameter at the second historical time. Based on the function and the first historical time, the second value of the key process parameter at the first historical time is determined. Here, the second historical time refers to any historical time other than the first historical time.

[0109] The process of generating the function corresponding to the key process parameter based on the first value of the key process parameter at the second historical time includes: generating a univariate linear function based on the first value of the key process parameter at the second historical time and the second historical time, and determining the univariate linear function as the function corresponding to the key process parameter.

[0110] For example, the first value of the key process parameter at the first second historical time x1 is y1, and the first value of the key process parameter at the second second historical time x2 is y2. Based on x1, x2, y1, and y2, the function y = ax + b for the key process parameter is generated. Here, a is a non-zero value, and b is an arbitrary value.

[0111] Optionally, the process of determining the second value of the key process parameter at the first historical time based on the function corresponding to the key process parameter and the first historical time includes: substituting the first historical time into the function corresponding to the key process parameter to obtain the second value of the key process parameter at the first historical time.

[0112] In step 204, based on the second values ​​of the key process parameters at various historical times, the production fluctuation early warning model corresponding to the key process parameters is obtained. The production fluctuation early warning model corresponding to the key process parameters is used to predict the values ​​of the key process parameters at the target time.

[0113] The target time is later than each historical time and adjacent to the latest time among all historical times. For example, if each historical time is from 12:31 on February 1, 2023 to 13:01 on February 1, 2023, then the target time is 13:02 on February 1, 2023.

[0114] In one possible implementation, the process of obtaining the production fluctuation early warning model corresponding to the key process parameter based on the second value of the key process parameter at each historical time includes: inputting each historical time into the initial model to obtain the first predicted value corresponding to each historical time; determining the first loss value based on the first predicted value corresponding to each historical time and the second value of the key process parameter at each historical time; and determining the initial model as the production fluctuation early warning model corresponding to the key process parameter if the first loss value is lower than the loss threshold.

[0115] In another possible implementation, if the first loss value is not lower than the loss threshold, the model parameters of the initial model are adjusted to obtain an adjusted model; each historical time is input into the adjusted model to obtain the second predicted value corresponding to each historical time; based on the second predicted value corresponding to each historical time and the second value of the key process parameter at each historical time, the second loss value is determined; if the second loss value is lower than the loss threshold, the adjusted model is determined to be the production fluctuation early warning model corresponding to the key process parameter.

[0116] If the second loss value is not lower than the loss threshold, continue to adjust the initial model until the loss value determined based on the adjusted model is lower than the loss threshold. Then, determine the adjusted model as the production fluctuation early warning model corresponding to the key process parameters.

[0117] The loss threshold is set based on experience or adjusted according to the implementation environment; this application does not limit this.

[0118] The initial model can be an LSTM (Long Short-Term Memory) model, which consists of three layers: an input layer, a hidden layer, and an output layer.

[0119] In one possible implementation, the second values ​​of the key process parameters at various historical time points can be divided into a training set and a test set, where each set includes at least one second value. The training set can be used to train an initial model, resulting in a production fluctuation early warning model corresponding to the key process parameters. The test set is then used to test the production fluctuation early warning model corresponding to the key process parameters to verify its predictive accuracy.

[0120] It should be noted that when there are multiple key process parameters, each key process parameter corresponds to a production fluctuation early warning model. The process for determining the production fluctuation early warning model corresponding to each key process parameter is similar, and can be found in the above-mentioned process for determining the production fluctuation early warning model corresponding to the key process parameter. This application embodiment will not repeat the details here.

[0121] like Figure 3 This is a schematic diagram illustrating the process of determining a production fluctuation model corresponding to a key process parameter, as provided in an embodiment of this application. In this process, historical data for each process parameter is acquired, key process parameters are identified among them, and based on the confidence value of the first value of the key process parameter at each historical time, the first value of the key process parameter at each historical time is processed to obtain the second value of the key process parameter at each historical time. Based on the second value of the key process parameter at each historical time, the initial model is trained to obtain a production fluctuation early warning model corresponding to the key process parameter.

[0122] Optionally, during training, the Backpropagation Through Time (BPTT) algorithm is employed. This algorithm optimizes the model's parameters by repeatedly performing forward propagation (calculating the model's predictions and loss) and backpropagation (calculating gradients and updating weights). In each iteration, the optimizer updates the model's weights based on the calculated gradients. To prevent overfitting and improve the model's generalization ability, the model is evaluated at the end of each epoch (training round), and the ReduceLROnPlateau (learning rate scheduler) method is used to adjust the learning rate or set early stopping to terminate training prematurely.

[0123] After obtaining the production fluctuation early warning model corresponding to the key process parameters, it is also possible to predict the values ​​of the key process parameters at the target time.

[0124] The process of predicting the values ​​of key process parameters at the target time includes: inputting the target time into the production fluctuation early warning model corresponding to the key process parameter, and obtaining the values ​​of the key process parameter at the target time.

[0125] like Figure 4 This is a flowchart illustrating the usage process of a production fluctuation early warning model corresponding to a key process parameter, as provided in an embodiment of this application. The target time is input into the production fluctuation early warning model corresponding to the key process parameter, and the output of the model is used as the value of the key process parameter at the target time.

[0126] After obtaining the values ​​of key process parameters at the target time, a fluctuation curve for the key process parameters can be generated based on the second values ​​of the key process parameters at various historical times and the values ​​at the target time. Based on the fluctuation curve, if production fluctuations are identified in the key process parameters, an early warning is issued according to the target warning method. Production fluctuations in key process parameters include anomalies in the reference portion of the fluctuation curve, which is the portion between the latest historical time and the target time.

[0127] Optionally, an anomaly in the reference portion includes situations where the trend of the reference portion differs from the trend of the portion of the fluctuation curve excluding the reference portion. Specifically, the trend of the reference portion is either an upward or downward trend, and the trend of the portion of the fluctuation curve excluding the reference portion is either an upward or downward trend. There are four possible implementation methods to determine whether production fluctuations have occurred in the reference portion.

[0128] In the first possible implementation, if the trend of the reference portion is downward, while the trend of the portion of the fluctuation curve other than the reference portion is upward, then the reference portion is abnormal.

[0129] In the second possible implementation, if the trend of the reference portion is downward, and the trend of the portion of the fluctuation curve other than the reference portion is downward, then the reference portion is not abnormal.

[0130] In the third possible implementation, if the trend of the reference portion is upward and the trend of the portion of the fluctuation curve other than the reference portion is upward, then the reference portion is not abnormal.

[0131] In the fourth possible implementation, if the trend of the reference portion is upward, while the trend of the portion of the fluctuation curve other than the reference portion is downward, then the reference portion is abnormal.

[0132] When it is determined that a key process parameter has caused a production fluctuation, the process of issuing an early warning according to the target early warning method includes at least one of the following: displaying a notification message, which indicates that a key process parameter has caused a production fluctuation; sending a notification message to the terminal device corresponding to the managed object; and playing voice data, which indicates that a key process parameter has caused a production fluctuation.

[0133] The voice data can be generated based on notification messages, and this application embodiment does not limit the content of the voice data. Sending notification messages to the terminal device corresponding to the managed object can be done via SMS or email, and this application embodiment does not limit the method of sending notification information to the terminal device corresponding to the managed object. The managed object can be a technician of the refining unit, or other objects, and this application embodiment does not limit this as well.

[0134] In one possible implementation, the refining unit includes multiple devices. When production fluctuates due to critical process parameters, the device corresponding to the critical process parameter can be identified, a solution for that device can be determined, and the solution can be sent to the terminal device corresponding to the managed object, enabling the managed object to resolve the issue according to the solution. This implementation can quickly locate the cause of the anomaly, helping technicians analyze the cause, shortening the anomaly handling time, and reducing production losses.

[0135] The computer equipment stores solutions for each device. When production fluctuations are detected due to key process parameters, the solution for the device corresponding to the key process parameters is determined from the solutions for each device.

[0136] The aforementioned method identifies the key process parameters affecting production fluctuations in the refining unit from among various process parameters. Then, based on historical data of these key process parameters, it obtains a corresponding production fluctuation early warning model. This model is used to predict the values ​​of the key process parameters at a target time, which determines whether production fluctuations have occurred. If a production fluctuation is imminent, a timely warning is issued and addressed. This allows for rapid identification of potential production fluctuations and provides sufficient time for technicians to resolve issues before they occur. Furthermore, more precise monitoring and timely warnings reduce the number of production interruptions in the refining unit, improving its production efficiency. In addition, since production fluctuations can potentially lead to safety hazards such as equipment damage and environmental pollution, real-time monitoring and early warnings help to promptly identify and address potential safety issues, thereby improving the safety of the production process.

[0137] Figure 5 The diagram shown is a structural schematic of a device for acquiring a production fluctuation early warning model according to an embodiment of this application. Figure 5 As shown, the device includes:

[0138] The acquisition module 501 is used to acquire historical data of various process parameters of the refining and chemical unit. The historical data of any process parameter includes the first value of any process parameter at each historical time and the confidence value of the first value.

[0139] The determination module 502 is used to determine the key process parameters among various process parameters. The key process parameters are the process parameters that affect the production fluctuations of the refining and chemical unit.

[0140] The processing module 503 is used to process the first value of the key process parameter at each historical time based on the confidence value of the first value of the key process parameter at each historical time, so as to obtain the second value of the key process parameter at each historical time.

[0141] The acquisition module 501 is also used to acquire the production fluctuation early warning model corresponding to the key process parameter based on the second value of the key process parameter at each historical time. The production fluctuation early warning model corresponding to the key process parameter is used to predict the value of the key process parameter at the target time. The target time is later than each historical time and adjacent to the latest time among each historical time.

[0142] In one possible implementation, the determining module 502 is used to determine the correlation coefficient between any two process parameters based on the first values ​​of each process parameter at each historical time. The correlation coefficient between any two process parameters is used to indicate the correlation between the two process parameters. Based on the correlation coefficient between any two process parameters, the key process parameters are determined among the various process parameters.

[0143] In one possible implementation, module 502 is used to determine the coefficient of each process parameter based on the correlation coefficient between any two process parameters. The coefficient of any process parameter is used to indicate the degree of influence of any process parameter on the production fluctuation of the refining and chemical unit. Based on the coefficient of each process parameter, each process parameter is sorted according to the target order to obtain the sorting result. The process parameters that meet the sorting requirements in the sorting result are determined as key process parameters.

[0144] In one possible implementation, the determining module 502 is used to determine at least one target correlation coefficient among the correlation coefficients between any two process parameters for any process parameter, wherein any target correlation coefficient is the correlation coefficient between any process parameter and a reference process parameter, and the reference process parameter is the process parameter other than any process parameter among the process parameters; the average value of the at least one target correlation coefficient is determined to be the coefficient of any process parameter.

[0145] In one possible implementation, the processing module 503 is configured to: determine the first value of the key process parameter at each historical time as the second value of the key process parameter at each historical time, provided that the confidence value of the first value of the key process parameter at each historical time is not less than the confidence threshold; generate a function corresponding to the key process parameter based on the first value of the key process parameter at the second historical time, provided that the confidence value of the first value of the key process parameter at the first historical time is less than the confidence threshold; and determine the second value of the key process parameter at the first historical time based on the function corresponding to the key process parameter and the first historical time, wherein the second historical time is any historical time other than the first historical time.

[0146] In one possible implementation, the acquisition module 501 is used to input each historical time into the initial model to obtain the first predicted value corresponding to each historical time; determine the first loss value based on the first predicted value corresponding to each historical time and the second value of the key process parameter at each historical time; adjust the model parameters of the initial model to obtain the adjusted model if the first loss value is not lower than the loss threshold; input each historical time into the adjusted model to obtain the second predicted value corresponding to each historical time; determine the second loss value based on the second predicted value corresponding to each historical time and the second value of the key process parameter at each historical time; and determine the adjusted model as the production fluctuation early warning model corresponding to the key process parameter if the second loss value is lower than the loss threshold.

[0147] In one possible implementation, the determining module 502 is also used to input the target time into the production fluctuation early warning model corresponding to the key process parameters, and obtain the value of the key process parameters at the target time.

[0148] In one possible implementation, the device further includes:

[0149] The generation module is used to generate the fluctuation curve of the key process parameter based on the second value of the key process parameter at each historical time and the value of the key process parameter at the target time.

[0150] The early warning module is used to issue early warnings according to the target early warning method when production fluctuations occur in key process parameters based on the fluctuation curve. Production fluctuations in key process parameters include anomalies in the reference part of the fluctuation curve, which is the part between the latest time in history and the target time.

[0151] In one possible implementation, the reference exceptions include:

[0152] The trend of the reference portion differs from the trend of the portion of the fluctuation curve excluding the reference portion.

[0153] In one possible implementation, the early warning module is configured to perform at least one of the following: display a notification message indicating an abnormality in a key process parameter; send a notification message to the terminal device corresponding to the managed object; and play voice data indicating an abnormality in a key process parameter.

[0154] The aforementioned device identifies key process parameters affecting production fluctuations in the refining unit. Based on historical data of these key parameters, it obtains a corresponding production fluctuation early warning model. This model then predicts the value of the key process parameter at a target time, confirming whether a production fluctuation has occurred. If a production fluctuation is imminent, a timely warning is issued and addressed. This rapid identification of potential production fluctuations and early warning before malfunctions occur provides technicians with sufficient time to resolve the issue. Furthermore, more precise monitoring and timely warnings reduce the number of production interruptions in the refining unit, improving its efficiency. In addition, since production fluctuations can lead to safety hazards such as equipment damage and environmental pollution, real-time monitoring and early warnings help identify and address potential safety issues promptly, thereby improving the safety of the production process.

[0155] It should be understood that the above-described apparatus is only illustrated by the division of the functional modules described above when implementing its functions. In practical applications, the functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0156] Figure 6 This illustration shows a structural block diagram of a terminal device 600 provided in an exemplary embodiment of this application. The terminal device 600 can be any electronic device product capable of human-computer interaction with a user through one or more methods such as a keyboard, touchpad, remote control, voice interaction, or handwriting device. Examples include PCs (Personal Computers), mobile phones, smartphones, PDAs (Personal Digital Assistants), wearable devices, PPCs (Pocket PCs), tablet computers, smart car systems, smart TVs, smart speakers, and smartwatches.

[0157] Typically, terminal device 600 includes a processor 601 and a memory 602.

[0158] Processor 601 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0159] The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 602 is used to store at least one instruction, which is executed by the processor 601 to implement the method for obtaining a production fluctuation early warning model provided in the method embodiments of this application.

[0160] In some embodiments, the terminal device 600 may also optionally include a peripheral device interface 603 and at least one peripheral device. The processor 601, memory 602, and peripheral device interface 603 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 604, a display screen 605, a camera assembly 606, an audio circuit 607, and a power supply 608.

[0161] Peripheral interface 603 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 601 and memory 602. In some embodiments, processor 601, memory 602 and peripheral interface 603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 601, memory 602 and peripheral interface 603 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0162] The radio frequency (RF) circuit 604 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 604 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 604 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 604 can communicate with other terminal devices through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 604 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0163] Display screen 605 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 605 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 601 for processing. In this case, display screen 605 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 605, disposed on the front panel of terminal device 600; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal device 600 or in a folded design; in still other embodiments, display screen 605 may be a flexible display screen, disposed on a curved or folded surface of terminal device 600. Furthermore, display screen 605 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 605 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0164] The camera assembly 606 is used to acquire images or videos. Optionally, the camera assembly 606 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal device 600, and the rear-facing camera is located on the back of the terminal device 600. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 606 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0165] The audio circuit 607 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 601 for processing, or input to the radio frequency circuit 604 to achieve voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located at a different part of the terminal device 600. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 601 or the radio frequency circuit 604 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 607 may also include a headphone jack.

[0166] Power supply 608 is used to supply power to the various components in terminal device 600. Power supply 608 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 608 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0167] In some embodiments, the terminal device 600 further includes one or more sensors 609. The one or more sensors 609 include, but are not limited to, an accelerometer 610, a gyroscope 611, a pressure sensor 612, an optical sensor 613, and a proximity sensor 614.

[0168] Accelerometer 610 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by terminal device 600. For example, accelerometer 610 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 601 can control display screen 605 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 610. Accelerometer 610 can also be used for games or for acquiring user motion data.

[0169] The gyroscope sensor 611 can detect the orientation and rotation angle of the terminal device 600. The gyroscope sensor 611 can work in conjunction with the accelerometer sensor 610 to collect the user's 3D movements on the terminal device 600. Based on the data collected by the gyroscope sensor 611, the processor 601 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0170] The pressure sensor 612 can be disposed on the side bezel of the terminal device 600 and / or on the lower layer of the display screen 605. When the pressure sensor 612 is disposed on the side bezel of the terminal device 600, it can detect the user's grip signal on the terminal device 600, and the processor 601 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 612. When the pressure sensor 612 is disposed on the lower layer of the display screen 605, the processor 601 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 605. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0171] An optical sensor 613 is used to collect ambient light intensity. In one embodiment, the processor 601 can control the display brightness of the display screen 605 based on the ambient light intensity collected by the optical sensor 613. Specifically, when the ambient light intensity is high, the display brightness of the display screen 605 is increased; when the ambient light intensity is low, the display brightness of the display screen 605 is decreased. In another embodiment, the processor 601 can also dynamically adjust the shooting parameters of the camera assembly 606 based on the ambient light intensity collected by the optical sensor 613.

[0172] The proximity sensor 614, also known as a distance sensor, is typically mounted on the front panel of the terminal device 600. The proximity sensor 614 is used to detect the distance between the user and the front of the terminal device 600. In one embodiment, when the proximity sensor 614 detects that the distance between the user and the front of the terminal device 600 is gradually decreasing, the processor 601 controls the display screen 605 to switch from a screen-on state to a screen-off state; when the proximity sensor 614 detects that the distance between the user and the front of the terminal device 600 is gradually increasing, the processor 601 controls the display screen 605 to switch from a screen-off state to a screen-on state.

[0173] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the terminal device 600, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0174] Figure 7This is a schematic diagram of the server structure provided in the embodiments of this application. The server 700 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 701 and one or more memories 702. The one or more memories 702 store at least one line of program code, which is loaded and executed by the one or more processors 701 to implement the production fluctuation early warning model acquisition method provided in the various method embodiments described above. Of course, the server 700 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 700 may also include other components for implementing device functions, which will not be elaborated here.

[0175] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one piece of program code that is loaded and executed by a processor to enable a computer to implement any of the above-described methods for obtaining a production fluctuation early warning model.

[0176] Optionally, the aforementioned computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0177] In an exemplary embodiment, a computer program or computer program product is also provided, which stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement any of the above-described methods for obtaining a production fluctuation early warning model.

[0178] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0179] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0180] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0181] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for obtaining a production fluctuation early warning model, characterized in that, The method includes: Historical data of various process parameters of the refining and chemical unit are obtained. The historical data of any process parameter includes the first value of the process parameter at each historical time and the confidence value of the first value. Among the various process parameters, key process parameters are identified, which are the process parameters that affect the production fluctuations of the refining and chemical unit. Based on the confidence value of the first value of the key process parameter at each historical time, the first value of the key process parameter at each historical time is processed to obtain the second value of the key process parameter at each historical time. Based on the second values ​​of the key process parameters at each historical time, a production fluctuation early warning model corresponding to the key process parameters is obtained. The production fluctuation early warning model corresponding to the key process parameters is used to predict the values ​​of the key process parameters at a target time. The target time is later than each historical time and adjacent to the latest time among each historical time.

2. The method according to claim 1, characterized in that, The determination of key process parameters among the various process parameters includes: Based on the first values ​​of each process parameter at each historical time, the correlation coefficient between any two process parameters is determined, and the correlation coefficient between any two process parameters is used to indicate the correlation relationship between the two process parameters. Based on the correlation coefficient between any two process parameters, the key process parameters are determined among the various process parameters.

3. The method according to claim 2, characterized in that, The step of determining the key process parameter among the various process parameters based on the correlation coefficient between any two process parameters includes: Based on the correlation coefficient between any two process parameters, the coefficient of each process parameter is determined, and the coefficient of any process parameter is used to indicate the degree of influence of any process parameter on the production fluctuation of the refining and chemical unit. Based on the coefficients of each process parameter, the process parameters are sorted according to the target order to obtain the sorting result; The process parameters that meet the sorting requirements in the sorting results are identified as the key process parameters.

4. The method according to claim 3, characterized in that, The step of determining the coefficients of each process parameter based on the correlation coefficient between any two process parameters includes: For any process parameter among the various process parameters, at least one target correlation coefficient is determined from the correlation coefficients between any two process parameters. Any target correlation coefficient is the correlation coefficient between any process parameter and a reference process parameter. The reference process parameter is the process parameter other than any process parameter among the various process parameters. The average value of the at least one target correlation coefficient is determined to be the coefficient of any one of the process parameters.

5. The method according to any one of claims 1 to 4, characterized in that, The step of processing the first value of the key process parameter at each historical time based on the reliability value of the first value of the key process parameter at each historical time to obtain the second value of the key process parameter at each historical time includes: If the confidence value of the first value of the key process parameter at each historical time is not less than the confidence threshold, the first value of the key process parameter at each historical time is determined as the second value of the key process parameter at each historical time. If the confidence value of the first value of the key process parameter at the first historical time is less than the confidence threshold, a function corresponding to the key process parameter is generated based on the first value of the key process parameter at the second historical time; and a second value of the key process parameter at the first historical time is determined based on the function corresponding to the key process parameter and the first historical time. The second historical time refers to the historical time other than the first historical time among the various historical times.

6. The method according to any one of claims 1 to 4, characterized in that, The step of obtaining the production fluctuation early warning model corresponding to the key process parameter based on the second value of the key process parameter at various historical times includes: Input each historical time into the initial model to obtain the first predicted value corresponding to each historical time; The first loss value is determined based on the first predicted value corresponding to each historical time and the second value of the key process parameter at each historical time. If the first loss value is not lower than the loss threshold, the model parameters of the initial model are adjusted to obtain the adjusted model; The historical time is input into the adjustment model to obtain the second predicted value corresponding to each historical time. The second loss value is determined based on the second predicted value corresponding to each historical time and the second value of the key process parameter at each historical time. If the second loss value is lower than the loss threshold, the adjustment model is determined to be the production fluctuation early warning model corresponding to the key process parameter.

7. The method according to any one of claims 1 to 4, characterized in that, After obtaining the production fluctuation early warning model corresponding to the key process parameter based on the second value of the key process parameter at each historical time, the method further includes: The target time is input into the production fluctuation early warning model corresponding to the key process parameter to obtain the value of the key process parameter at the target time.

8. The method according to claim 7, characterized in that, The method further includes: Based on the second values ​​of the key process parameters at each historical time and the values ​​of the key process parameters at the target time, a fluctuation curve of the key process parameters is generated. If, based on the fluctuation curve, it is determined that the key process parameter has experienced production fluctuations, an early warning is issued according to the target early warning method. The production fluctuation of the key process parameter includes an anomaly in the reference portion of the fluctuation curve, where the reference portion is the part between the latest time in the historical time and the target time.

9. The method according to claim 8, characterized in that, The anomaly in the reference portion includes: The trend of the reference portion is different from the trend of the portion of the fluctuation curve other than the reference portion.

10. The method according to claim 8, characterized in that, The method of issuing warnings according to the target warning method includes at least one of the following: Display a notification message, which indicates that the key process parameter has become abnormal; Send the notification message to the terminal device corresponding to the managed object; Play voice data, which is used to indicate that the key process parameters are abnormal.

11. A device for acquiring a production fluctuation early warning model, characterized in that, The device includes: The acquisition module is used to acquire historical data of various process parameters of the refining and chemical unit. The historical data of any process parameter includes the first value of the process parameter at each historical time and the confidence value of the first value. A determination module is used to determine key process parameters among the various process parameters, wherein the key process parameters are process parameters that affect the production fluctuations of the refining and chemical unit; The processing module is used to process the first value of the key process parameter at each historical time according to the confidence value of the first value of the key process parameter at each historical time, so as to obtain the second value of the key process parameter at each historical time. The acquisition module is further configured to acquire a production fluctuation early warning model corresponding to the key process parameter based on the second values ​​of the key process parameter at each historical time. The production fluctuation early warning model corresponding to the key process parameter is used to predict the value of the key process parameter at a target time. The target time is later than each historical time and adjacent to the latest time among each historical time.

12. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one piece of program code, which is loaded and executed by the processor to enable the computer device to implement the method for obtaining the production fluctuation early warning model as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to enable the computer to implement the method for obtaining the production fluctuation early warning model as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, The computer program product stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement the method for obtaining the production fluctuation early warning model as described in any one of claims 1 to 10.

Images