Internet of Things monitoring method for air separation device based on DCSPLC serial port

Abstract

The present invention relates to an air separation device IoT monitoring method based on a DCSPLC serial port, and relates to the field of IoT communication technology, including: after the air separation device is started, a timer is started, and when the timing information meets a preset duration, the DCSPLC serial port sends the air separation device control parameters and the air separation device state parameters to an IoT module, and the timing information is reset to zero; when the air separation device control parameters and the air separation device state parameters are received, a cloud server is requested to download coding constraints, and cloud server feedback information is obtained; when the cloud server feedback information includes zero-knowledge coding constraints, the air separation device control parameters and the air separation device state parameters are zero-knowledge encoded, and the zero-knowledge encoding results are obtained and sent to the cloud server for decoding and storage. The present invention solves the technical problem that there is a risk of data leakage in the data transmission process of the air separation device due to the lack of a security protection mechanism for data transmission, and improves the privacy security and reliability of data transmission.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things communication, and in particular to an Internet of Things monitoring method for an air separation device based on a DCSPLC serial port. Background Art

[0002] As an important infrastructure in industrial production, real-time monitoring and data transmission of the operating status of air separation units are crucial to ensuring safe and efficient production. With the rapid development of Internet of Things technology, IoT monitoring of air separation units has gradually become one of the core links of intelligent industrial systems. By collecting, transmitting and analyzing the operating data of air separation units, precise control of the operation of the unit and risk prediction can be achieved.

[0003] Traditional IoT monitoring methods usually use external networks to directly access operator stations or industrial control networks to collect air separation unit operation data. Although these methods can meet basic data transmission needs, the security of data transmission faces challenges. In existing methods, data is basically transmitted and stored in plain text. Even if security devices such as firewalls and isolation gateways are added to the network, it is difficult to completely eliminate the security risks of control network intrusion, which is easy to cause data leakage risks and is difficult to meet the needs of modern industry for safe and efficient IoT monitoring of air separation units. Summary of the invention

[0004] The present invention aims to solve the technical problem that the data transmission process of an air separation device has a risk of data leakage due to the lack of a security protection mechanism for data transmission in the prior art, and provides an air separation device IoT monitoring method based on a DCSPLC serial port to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The invention provides an air separation device Internet of Things monitoring method based on a DCS PLC serial port, which is applied to an Internet of Things module and comprises: receiving an air separation device control parameter and an air separation device state parameter transmitted from a DCS PLC serial port, wherein when the air separation device is started, a timer is started, and when timing information meets a preset time length, the DCS PLC serial port will send the air separation device control parameter and the air separation device state parameter to the Internet of Things module based on an RS485 communication protocol, and reset the timing information to zero to start timing; when the air separation device control parameter and the air separation device state parameter are received, a cloud server is requested to download coding constraints to obtain cloud server feedback information; when the cloud server feedback information includes zero-knowledge coding constraints, zero-knowledge coding is performed on the air separation device control parameter and the air separation device state parameter to obtain a zero-knowledge coding result; and the zero-knowledge coding result is sent to the cloud server for decoding and storage.

[0007] The beneficial effects of the present invention are: by starting a timer to control the triggering timing of data transmission, the timed collection and update of the operating status of the air separation unit can be achieved, the real-time and synchronization of data transmission can be ensured, and the waste of resources caused by information lag or frequent transmission can be avoided. After receiving the control parameters and status parameters of the air separation unit, the cloud server is promptly requested to provide zero-knowledge coding constraint information to provide necessary rules and basis for subsequent data encryption, ensuring that the encoding process is consistent with the cloud decoding process. The control parameters and status parameters of the air separation unit are zero-knowledge encoded using the coding constraints provided by the cloud server to prevent data leakage during transmission, while meeting the privacy protection requirements in the industrial Internet of Things environment. The encrypted data is transmitted to the cloud server, which is decoded and stored by the cloud to ensure the security and availability of data stored in the cloud, providing a reliable basis for subsequent data analysis and intelligent monitoring.

[0008] In summary, the present invention realizes the efficient collection and transmission of air separation unit data by introducing a timing trigger mechanism, significantly enhances the privacy protection capability in the data transmission process by using zero-knowledge coding technology, and optimizes the reliability of data transmission by combining the RS485 protocol and cloud decoding and storage mechanism, thereby improving the real-time and security of the industrial Internet of Things system, and providing technical support for the efficient monitoring and intelligent management of air separation units. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a DCSPLC serial port-based air separation device IoT monitoring method provided by the present invention;

[0010] Figure 2 A schematic diagram of a process for obtaining a zero-knowledge coding result in a DCSPLC serial port-based air separation device IoT monitoring method provided by the present invention;

[0011] Figure 3 A schematic diagram of the process of sending the zero-knowledge coding result to the cloud server for decoding and storage in the DCSPLC serial port-based air separation device IoT monitoring method provided by the present invention. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] like Figure 1 As shown, an embodiment of the present invention provides an air separation device IoT monitoring method based on a DCSPLC serial port, and the method is applied to an IoT module, comprising:

[0016] Step S1: receiving the air separation unit control parameters and air separation unit status parameters transmitted from the DCS PLC serial port, wherein when the air separation unit is started, the timer is started, and when the timing information meets the preset duration, the DCS PLC serial port will send the air separation unit control parameters and air separation unit status parameters to the Internet of Things module based on the RS485 communication protocol, and reset the timing information to zero to start timing.

[0017] Specifically, DCSPLC serial port refers to DCS (distributed control system) serial port and PLC (programmable logic controller) serial port. DCS (distributed control system) and PLC (programmable logic controller) are commonly used control systems in air separation units. The two work together to control the operation of the air separation unit and record the operation data of the air separation unit. The RS485 communication protocol is a commonly used industrial-grade serial communication standard with strong anti-interference ability, long transmission distance (up to 1200 meters) and multi-point communication. It is suitable for multi-device data transmission in industrial scenarios. In industrial systems, timers are functional modules used to accurately calculate time intervals.

[0018] When the air separation unit is started, the timer starts working and counts according to the pre-set duration. During the timing period, the DCS serial port and the PLC serial port are in a waiting state. When the timing information reaches the preset duration, the DCS serial port and the PLC serial port will send the collected air separation unit control parameters and air separation unit status parameters to the Internet of Things module according to the RS485 communication protocol. After each data transmission, the timer will be reset to zero and restart the timing to ensure that the data transmission is carried out at a fixed interval. Among them, the air separation unit control parameters are parameters used to control the operation of the air separation unit, such as pressure, temperature, flow, valve opening and closing, etc.; the air separation unit status parameters are parameters that reflect the current operating status of the air separation unit, such as equipment operating status, alarm information, etc.

[0019] Acquiring data from the two sources of DCS serial port and PLC serial port can make the acquired air separation unit control and status information more comprehensive and accurate. The timer setting can effectively control the frequency of data transmission, avoid data transmission too frequently, and reduce the burden on the network. At the same time, sending data at a certain time interval helps to improve the orderliness of data transmission, ensure that the IoT module receives relatively stable and regular data, and improve the reliability of data transmission.

[0020] Step S2: When the air separation device control parameter and the air separation device state parameter are received, a cloud server is requested to download coding constraints to obtain cloud server feedback information.

[0021] Specifically, a cloud server can be any remote server that provides data storage and processing services, supporting large-scale data processing and storage. Coding constraints are rules and parameters used for data encoding to ensure the security and integrity of data during transmission. Feedback information is information returned by the cloud server containing coding constraints.

[0022] When the IoT module receives the air separation unit control parameters and air separation unit status parameters from the DCS serial port and PLC serial port, it immediately sends a request to the cloud server through the network, requesting the download coding constraints applicable to this transmission. The cloud server returns feedback information based on the system's coding rules, including the constraints or encryption keys required for coding. By dynamically obtaining coding constraints, it can ensure that subsequent data processing matches the standards of the cloud server, thereby ensuring the consistency and accuracy of data encryption and facilitating subsequent secure transmission.

[0023] Step S3: When the cloud server feedback information includes zero-knowledge coding constraints, zero-knowledge coding is performed on the air separation device control parameters and the air separation device state parameters to obtain zero-knowledge coding results.

[0024] Specifically, zero-knowledge coding is a cryptographic technology that allows encoding operations to be performed without revealing the actual content of the data during the encoding process. The IoT module performs zero-knowledge encoding on the air separation unit control parameters and air separation unit status parameters according to the zero-knowledge coding constraints returned by the cloud server to obtain zero-knowledge encoding results. The encoding process can use symmetric encryption (such as AES) or asymmetric encryption (such as RSA) algorithms to convert plaintext data into ciphertext while retaining the keys or rules required for decoding.

[0025] Zero-knowledge coding greatly improves data security. During data transmission, even if the data is intercepted, the interceptor cannot obtain the true content of the data due to the use of zero-knowledge coding, thus protecting sensitive information such as the control and status of the air separation unit obtained from the DCS serial port and PLC serial port.

[0026] Step S4: Send the zero-knowledge encoding result to the cloud server for decoding and storage.

[0027] Specifically, the IoT module uploads the ciphertext data (zero-knowledge encoding result) after zero-knowledge encoding to the cloud server through network communication (based on network transmission protocols such as TCP / IP protocol). After receiving the ciphertext, the cloud server decodes the data through the internal decryption module using the corresponding key or rule, restores it to readable plaintext, and stores it in the database. While ensuring the security of data transmission, cloud storage realizes efficient data management, provides a reliable data foundation for subsequent intelligent analysis and monitoring, and also ensures the integrity of data in the entire IoT system.

[0028] Furthermore, step S2 further includes:

[0029] Step S21: when requesting to download coding constraints from the cloud server, performing coding constraint optimization on the cloud server, obtaining zero-knowledge coding constraints, and adding them into the cloud server feedback information.

[0030] Step S22: receiving the cloud server feedback information from the cloud server.

[0031] Specifically, when the IoT module requests the cloud server to download the coding constraints, the cloud server will analyze the requirements of the current task (such as data size, real-time requirements, device performance, etc.) and perform coding constraint optimization. The optimization process selects the encryption rule with the best security, efficiency and resource consumption in the current scenario by comparing and testing multiple encryption algorithms (such as AES, RSA, and zero-knowledge proof). For example, when the transmission task requires efficient processing of large-scale data, the cloud server may choose symmetric encryption (such as AES) as the priority solution; if the task is more concerned with security, it may choose a zero-knowledge proof algorithm. After the optimization is completed, the cloud server adds the selected zero-knowledge coding constraints to the feedback information. Through coding constraint optimization, the cloud server realizes dynamic adaptation of coding rules and improves the flexibility and security of data encryption.

[0032] The IoT module receives feedback information from the cloud server through the communication protocol, which contains the constraint details of zero-knowledge encoding, such as the encryption algorithm type (such as AES or zero-knowledge proof), encryption key or rules. After receiving the feedback information, the IoT module will parse and load the relevant encoding rules to prepare for subsequent data encryption operations.

[0033] The above steps enable efficient data interaction between the cloud server and the IoT module, providing reliable parameter support for subsequent data encryption.

[0034] Further, step S21 includes:

[0035] Step S211: Obtain a function curve library.

[0036] Step S212: Obtain a set of historical selection function curves according to the position number of the air separation unit.

[0037] Step S213: construct a function curve and select a fitness function:

[0038] ; ;in, Characterize the i-th function curve of the function curve library, The jth function curve representing the set of historically selected function curves, Characterizes the fitness of the i-th function curve, Characterize the weight of the jth function curve, represents the time interval from the last time the jth function curve was selected to the current time, N represents the number of historically selected function curve sets, Characterizes the distribution distance between the i-th function curve and the j-th function curve, and the distribution distance is characterized by the area of ​​the closed figure of the curve.

[0039] Step S214: Based on the historically selected function curve set, the function curve library is optimized in combination with the function curve selection fitness function to obtain a recommended function curve.

[0040] Step S215: setting the recommended function curve as the zero-knowledge coding constraint.

[0041] Specifically, the cloud server first loads the function curve library, which contains a variety of predefined function curves, each of which represents data distribution or parameter rules under specific conditions. For example, curve A may correspond to a linear encryption rule, and curve B may correspond to an exponential decay encryption rule. By loading the curve library, the cloud server has the basic data for the selection of function curves.

[0042] The air separation unit number is a specific number used to identify the air separation unit. In an industrial environment, each device has a unique number to identify, manage, and operate it. Based on the air separation unit number, the cloud server extracts the function curve set that has been actually selected for the device in past tasks from the historical records, namely the historical selected function curve set. The historical selected function curve set reflects the encryption requirements and environmental characteristics of the device, providing an important reference for the current optimization.

[0043] The fitness function for function curve selection is a function used to quantify the quality of candidate curves, helping to select the function curve that best suits the current task. For each function curve in the function curve library , select a function curve from the function curve set based on its historical The distribution distance , the weight of the historical selection function curve Factors such as Among them, the distribution distance Characterizes the distribution distance between the i-th function curve and the j-th function curve, represented by the closed graph area of ​​the curve. The smaller the area, the more similar the shapes of the two curves are, and the higher the matching degree. Indicates the influence of the most recently used function curve on the current selection, calculated based on the time interval from the last time it was selected to the current time. The shorter the time interval, the higher the weight.

[0044] This function curve uses a fitness function based on the distribution distance and weight of the historically selected function curves, and calculates the fitness value of each function curve by weighted summation. The higher the fitness value, the closer the distribution distance of the function curve to the historically selected function curve, the greater the weight, and therefore it is more suitable as a recommended function curve.

[0045] The fitness values ​​of all candidate function curves in the function curve library are calculated using the above function curve selection fitness and the historically selected function curve set, and the curve with the highest fitness value is selected as the recommended curve, and the recommended curve is used as the zero-knowledge coding constraint.

[0046] The above steps utilize the function curve to select the fitness function to select the best function curve with the highest fitness, which significantly enhances the security and flexibility of the data encryption process.

[0047] Further, such as Figure 2 As shown, step S3 includes:

[0048] Step S31: obtaining a first parameter distribution matrix of control parameters of the air separation unit.

[0049] Step S32: constructing a two-dimensional grid coordinate system based on the recommended function curve of the zero-knowledge encoding constraint.

[0050] Step S33: converting the first parameter distribution matrix into a first parameter distribution grid.

[0051] Step S34: coincide one corner of the first parameter distribution grid with the origin of the two-dimensional grid coordinate system, coincide two sides of the first parameter distribution grid with two axes of the two-dimensional grid coordinate system, and obtain an online distribution parameter value set, wherein the online distribution parameter value set has an online distribution coordinate set.

[0052] Step S35: Based on the online distribution coordinate set, the offline distribution parameter value set is encoded in combination with the offline distribution coordinate set to obtain the zero-knowledge encoding result.

[0053] Specifically, the first parameter distribution matrix is ​​a data structure in matrix form used to represent the distribution of control parameters of an air separation unit, and describes the changes of control parameters of an air separation unit in different states or time points in matrix form. For the collected control parameters of an air separation unit, these data are organized into a matrix form according to the parameter type, collection time sequence and other rules. For example, if an air separation unit has multiple control parameters such as temperature, pressure, flow rate, etc., and these parameters have different values ​​at different times, then a matrix can be constructed, with rows representing different times and columns representing different control parameters. The elements in the matrix are the values ​​of the corresponding control parameters at the corresponding times. The first parameter distribution matrix provides a unified and structured data basis for subsequent operations, and can clearly present the distribution of the control parameters of the air separation unit.

[0054] A two-dimensional grid coordinate system is constructed based on the characteristics of the recommended function curve in the zero-knowledge coding constraint. The value ranges of the x-axis and y-axis of the two-dimensional grid coordinate system are determined based on the domain and range of this function. Constructing a two-dimensional grid coordinate system enables subsequent parameter conversion and coding operations to be performed in a unified coordinate system, which is conducive to improving the accuracy and efficiency of coding.

[0055] A coordinate mapping operation is performed on each element in the first parameter distribution matrix. The row and column indexes in the matrix are mapped to the coordinate positions in the two-dimensional grid coordinate system using the matrix operation algorithm and the coordinate conversion algorithm, so as to convert the first parameter distribution matrix into the first parameter distribution grid. For example, if an element of the first parameter distribution matrix is ​​located in the i-th row and the j-th column, then it will be mapped to the coordinate (x i ,y j ). By converting the first parameter distribution matrix into the first parameter distribution grid, the control parameters of the air separation unit can be better combined with the two-dimensional grid coordinate system, laying the foundation for the subsequent extraction and encoding operations of parameters in the coordinate system.

[0056] One corner (e.g., the upper left corner) of the first parameter distribution grid is overlapped with the origin of the two-dimensional grid coordinate system, and the two sides (e.g., the upper side and the left side) of the first parameter distribution grid are overlapped with the two axes (x-axis and y-axis) of the two-dimensional grid coordinate system. Then, the elements in the first parameter distribution grid are traversed to determine whether they are located on the recommended function curve (here, it can be determined based on the mathematical relationship of the coordinates, for example, if the coordinate corresponding to a certain parameter value satisfies the equation of the recommended function curve or is within a specific deviation range on the line that coincides with the coordinate axis). If so, the coordinate is extracted and put into the online distribution coordinate set, and the parameter value corresponding to the coordinate is extracted and added to the online distribution parameter value set.

[0057] The offline distribution coordinate set is a coordinate set corresponding to the online distribution coordinate set, which is located in the two-dimensional grid coordinate system except for the recommended function curve. Similarly, the offline distribution coordinate set corresponds to the offline distribution parameter value set. The offline distribution parameter value is encrypted or converted using the relative relationship between the online distribution coordinates and the offline distribution coordinates to obtain a zero-knowledge encoding result.

[0058] The above steps achieve visualization and accurate distribution modeling of control parameters by recommending function curves and grid distribution. The combination of online and offline distribution achieves efficient encryption of parameters and ensures privacy and security of data transmission.

[0059] Further, step S35 includes:

[0060] Step S351: extracting the first on-line distribution coordinates until the Mth on-line distribution coordinates according to the on-line distribution coordinate set.

[0061] Step S352: partitioning the offline distribution coordinate set according to the first online distribution coordinates to the Mth online distribution coordinates to obtain first online distribution and offline distribution coordinate matching sets to the Mth online distribution and offline distribution coordinate matching sets.

[0062] Step S353: Taking the first online distribution coordinates as a reference, traverse the first online distribution and offline distribution coordinate matching sets to perform coordinate deviation encoding to obtain a coordinate deviation binary vector set.

[0063] Step S354: Based on the first online distribution coordinate parameter value, traverse the first online distribution line distribution coordinate matching parameter value set to perform deviation encoding to obtain a parameter value deviation unary vector set.

[0064] Step S355: Combine the one-to-one corresponding coordinate deviation binary vector set and the parameter value deviation one-element vector set to construct a first line distribution coordinate body three-element array set.

[0065] Step S356: constructing a first online distribution coordinate header ternary array using the first online distribution coordinates and the first online distribution coordinate parameter values.

[0066] Step S357: construct a first online distributed coordinate zero-knowledge encoding result according to the first online distributed coordinate header ternary array and the first online distributed coordinate body ternary array set.

[0067] Step S358: until the zero-knowledge coding result of the distribution coordinates on the Mth line is constructed.

[0068] Step S359: Add the zero-knowledge coding results of the first distribution coordinates on the line to the zero-knowledge coding results of the distribution coordinates on the Mth line into the zero-knowledge coding results.

[0069] Specifically, from the on-line distribution coordinate set, each coordinate is extracted in sequence and marked as the first on-line distribution coordinate until the Mth on-line distribution coordinate, where M is a positive integer and a preset number.

[0070] According to the first online distribution coordinates to the Mth online distribution coordinates, the offline distribution coordinate set is partitioned. Exemplarily, the online distribution coordinates are used as the center of the circle, different radius ranges are set, and the offline distribution coordinates are divided into different coordinate groups. Each coordinate group corresponds to an online distribution coordinate, and each coordinate group and the corresponding online distribution coordinate constitute an online distribution and offline distribution coordinate matching set. The first online distribution coordinates to the Mth online distribution coordinates correspond to the first online distribution and offline distribution coordinate matching set to the Mth online distribution and offline distribution coordinate matching set. This partitioning operation classifies the offline distribution coordinates according to their association with the online distribution coordinates, so that specific encoding operations can be performed for each matching set later, thereby improving the accuracy and efficiency of encoding.

[0071] Taking the first online distribution coordinates as the reference, traverse the first online distribution offline distribution coordinate matching set. For each offline distribution coordinate in the matching set, calculate its deviation from the first online distribution coordinate in the x and y directions to obtain a coordinate deviation binary vector set. For example, if the first online distribution coordinates are (x0, y0) and the offline distribution coordinates are (x, y), then the x-direction deviation is , y-direction deviation Then (Δx, Δy) is encoded into a binary vector to obtain the coordinate deviation binary vector of the coordinates distributed under the line.

[0072] Taking the first online distribution coordinate parameter value v0 as the reference, traverse the first online distribution line distribution coordinate matching parameter value set. For each parameter value in the matching parameter value set, calculate the difference Δv between it and the first online distribution coordinate parameter value v0, and then encode this difference into a one-element vector to obtain a parameter value deviation one-element vector set.

[0073] For the elements in the coordinate deviation binary vector set and the parameter value deviation univariate vector set, they are combined in a one-to-one correspondence to construct a first online distribution coordinate body ternary array set, where each body ternary array in the set corresponds to an offline distribution coordinate in the first online distribution offline distribution coordinate matching set. For example, if the coordinate deviation binary vector set is {(1, 2), (3, 4)}, and the parameter value deviation univariate vector set is {5, 6}, then the combined ternary array set is {(1, 2, 5), (3, 4, 6)}.

[0074] The first online distribution coordinates (x0, y0) and the first online distribution coordinate parameter value v0 are combined into a ternary array to obtain the first online distribution coordinate header ternary array (x0, y0, v0).

[0075] Combine the first online distributed coordinate head ternary array with each body ternary data in the first online distributed coordinate body ternary array set in the order of "head-body" to construct the first online distributed coordinate zero-knowledge encoding result. The first online distributed coordinate zero-knowledge encoding result includes several (x0, y0, v0) (x, y, v) arrays.

[0076] Similarly, for the second online distribution and offline distribution coordinate matching set up to the M-th online distribution and offline distribution coordinate matching set, calculation and encoding are performed according to similar operation steps for the first online distribution and offline distribution coordinate matching set to construct the second online distribution coordinate zero-knowledge encoding result up to the M-th online distribution coordinate zero-knowledge encoding result.

[0077] The zero-knowledge encoding results of the first online distribution coordinates until the zero-knowledge encoding results of the Mth online distribution coordinates are added to the final zero-knowledge encoding result in sequence. This result contains the encoding information of the entire online distribution coordinate set and its related offline distribution coordinates, realizes the zero-knowledge encoding of the offline distribution parameter value, and improves the security and confidentiality of the data.

[0078] Further, step S352 includes:

[0079] The offline distribution coordinate set is partitioned with the first online distribution coordinates to the M-th online distribution coordinates as the center coordinates to obtain a partition result; when the area variance of the partition result is less than or equal to the variance threshold, a matching set of the first online distribution and offline distribution coordinates is obtained until the M-th online distribution and offline distribution coordinates matching set.

[0080] Specifically, for each coordinate from the first online distribution coordinate to the Mth online distribution coordinate, use it as the center coordinate. Then, partition the offline distribution coordinate set according to a certain distance rule. For example, in a two-dimensional plane, the distance from the offline distribution coordinate (x, y) to the center coordinate (x i ,y i ). According to the size of the distance, the offline distribution coordinates are divided into different areas to obtain the partition results.

[0081] Next, the area variance of the partition result is calculated and compared with the variance threshold. This variance threshold is a pre-set value used to measure the uniformity of the partition result. When the area variance of the partition result is less than or equal to this threshold, it means that the difference in area of ​​the partition result is within an acceptable range. At this time, the first online distribution and offline distribution coordinate matching set is determined according to the partition result until the Mth online distribution and offline distribution coordinate matching set. This screening method based on the variance threshold can ensure the rationality and stability of the partition, making the subsequent encoding operations based on these matching sets more accurate and effective, thereby improving the reliability and security of the entire zero-knowledge encoding process.

[0082] Further, such as Figure 3 As shown, step S4 includes:

[0083] Step S41: On the cloud server, the zero-knowledge coding result is decoded according to the coding constraint to obtain the air separation device control parameter and the air separation device state parameter.

[0084] Step S42: performing state prediction according to the air separation unit control parameters to obtain standard state parameters of the air separation unit.

[0085] Step S43: Compare the standard state parameters of the air separation unit with the state parameters of the air separation unit to obtain a state deviation vector of the air separation unit.

[0086] Step S44: abnormal identification is performed on the state parameter of the air separation unit according to the state deviation vector of the air separation unit to obtain an abnormal identification result.

[0087] Step S45: storing the abnormal identification result, the air separation unit control parameter and the air separation unit state parameter.

[0088] Specifically, on the cloud server, the zero-knowledge encoding result is decoded according to the previously set encoding constraints. This process is the inverse process of encoding and needs to be restored according to the algorithm and rules used during encoding. Through the decoding operation, the control parameters and state parameters of the air separation unit can be accurately restored from the encoding results, providing original data for subsequent status analysis and monitoring of the air separation unit.

[0089] Load the pre-trained air separation unit state prediction model. Input the decoded control parameters into the prediction model, and the model will output the state parameters that the air separation unit should achieve under ideal conditions, that is, the standard state parameters.

[0090] Compare the actual value and standard value of each state parameter in the standard state parameter of the air separation unit with the state parameter of the air separation unit one by one to obtain the state deviation vector of the air separation unit. Deviation vector = actual state parameter − standard state parameter. This state deviation vector of the air separation unit is a multidimensional vector, which contains state deviations in multiple dimensions. By calculating the state deviation vector, we can intuitively understand the difference between the actual state and the standard state of the air separation unit, providing a basis for abnormal identification.

[0091] According to the state deviation vector of the air separation unit, the state parameters of the air separation unit are marked as abnormal, and the abnormal identification result is obtained. The abnormal identification can adopt a threshold-based judgment method. First, according to the process requirements and device performance of the air separation unit, the allowable deviation threshold is set for each state parameter to obtain the deviation threshold vector. Then, the deviation threshold vector and the state deviation vector of the air separation unit are compared, and the parameters exceeding the threshold are marked as abnormal values ​​to obtain the abnormal identification result. This abnormal identification result reflects whether there is an abnormality in the operating state of the air separation unit and the abnormal situation, which helps to quickly locate the abnormality in the operation of the air separation unit so that timely measures can be taken to repair or adjust it.

[0092] The abnormal identification results, air separation unit control parameters and air separation unit status parameters are stored. These data can be stored in a database (such as a relational database MySQL or a non-relational database MongoDB, etc.) or a file system (such as storing data in a local file or a file in a cloud storage in a specific format). By storing these data, it is convenient to query and analyze the operation history of the air separation unit in the future, which helps to optimize the control strategy and maintenance plan of the air separation unit.

[0093] The above steps restore the coded information to key parameters through decoding, and predict the standard state parameters, combine the deviation between the standard state and the actual state, accurately analyze the operation of the device, quickly discover anomalies and classify them, and provide data support for subsequent optimization, prediction and emergency management.

[0094] Further, step S42 includes:

[0095] Step S421: According to the model of the air separation unit, the control parameter record data of the air separation unit and the standard state record parameters of the air separation unit are collected.

[0096] Step S422: configuring an air separation device state prediction model using the air separation device control parameter record data and the air separation device standard state record parameters, and embedding the air separation device state prediction model into the cloud server.

[0097] Step S423: Processing the air separation unit control parameters according to the air separation unit state prediction model to obtain the air separation unit standard state parameters.

[0098] Specifically, the state prediction of the air separation unit is carried out according to the control parameters of the air separation unit to obtain the standard state parameters of the air separation unit, which can be realized by training the state prediction model of the air separation unit using a machine learning algorithm. First, according to the model of the air separation unit, the control parameter record data of the air separation unit of the model and the standard state record parameters of the air separation unit are obtained from a database or by using big data.

[0099] The acquired air separation unit control parameter record data and air separation unit standard state record parameters are used as training data, and supervised learning algorithms such as regression models (linear regression, polynomial regression) or machine learning models (random forest, support vector machine, neural network) are used to build an air separation unit state prediction model. After the model is built, it is deployed to a cloud server for easy access at any time. Exemplarily, a multi-layer perceptron model is selected for training, and the air separation unit control parameter record data is used as input data, and the air separation unit standard state record parameters are used as supervised output. A deep learning framework such as PyTorch or TensorFlow is used to continuously adjust the parameters of the multi-layer perceptron model so that its output gradually approaches the actual result (i.e., the air separation unit standard state record parameters) until the model converges.

[0100] On the cloud server, the control parameters of the air separation unit are input into the constructed air separation unit state prediction model. The model performs calculations based on the previously learned relationships to obtain the standard state parameters of the air separation unit. For example, if the control parameters of the air separation unit include temperature and pressure set values, the model will calculate the corresponding standard state parameters based on the previously learned relationship between the temperature and pressure set values ​​and other parameters (such as flow rate) under the standard state. This standard state parameter of the air separation unit provides a reference standard for subsequent comparison of actual state parameters and judgment of whether the air separation unit is abnormal, which helps to promptly discover and solve problems in the operation of the air separation unit.

[0101] The DCSPLC serial port-based air separation device IoT monitoring method provided by the embodiment of the present invention has at least the following technical effects:

[0102] The control parameters and state parameters of the air separation unit transmitted by the DCSPLC serial port based on the RS485 communication protocol are received through the Internet of Things module, and the timer is started to regularly update the data transmission, ensuring the stability and timeliness of data transmission, so that the monitoring system can obtain the operating status of the air separation unit in real time. After responding to the request, the cloud server performs coding constraint optimization, uses the fitness function of the function curve to select the function curve library, and combines the historical selection of the function curve to obtain the recommended function curve as the zero-knowledge coding constraint. Subsequently, a two-dimensional grid coordinate system is constructed according to the control parameters, and partition matching is performed between the online distribution coordinate set and the offline distribution coordinate set. The zero-knowledge coding result is generated by encoding the coordinate deviation and parameter value deviation, ensuring the privacy and security of the data during transmission and storage, and preventing data leakage. After decoding, the cloud server processes the control parameters of the air separation unit based on the embedded state prediction model to generate standard state parameters, and calculates the state deviation vector by comparing the standard state parameters with the actual state parameters. The deviation vector is used to identify abnormal states, and accurate state evaluation and abnormality detection of the air separation unit are performed, thereby improving the reliability of the device operation and the level of intelligent management.

[0103] In general, the embodiments of the present invention not only improve the reliability and real-time performance of the Internet of Things monitoring system of the air separation unit, but also significantly enhance the security and privacy protection of the data, thereby achieving the technical effect of improving the real-time performance and privacy security of data transmission.

[0104] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0105] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for monitoring the Internet of Things of air separation devices based on a DCSPLC serial port, characterized in that: Applied to IoT modules, including: Receiving air separation unit control parameters and air separation unit status parameters transmitted from the DCS PLC serial port, wherein when the air separation unit is started, starting the timer, when the timing information meets the preset time length, the DCS PLC serial port will send the air separation unit control parameters and air separation unit status parameters to the Internet of Things module based on the RS485 communication protocol, and at the same time reset the timing information to zero to start timing; When receiving the air separation device control parameter and the air separation device state parameter, requesting the cloud server to download the coding constraint and obtaining feedback information from the cloud server; When the cloud server feedback information includes a zero-knowledge coding constraint, performing zero-knowledge coding on the air separation device control parameter and the air separation device state parameter to obtain a zero-knowledge coding result; Sending the zero-knowledge encoding result to the cloud server for decoding and storage; Wherein, when the cloud server feedback information includes zero-knowledge coding constraints, zero-knowledge coding is performed on the air separation device control parameters and the air separation device state parameters to obtain a zero-knowledge coding result, including: Obtaining a first parameter distribution matrix of control parameters of the air separation unit; Constructing a two-dimensional grid coordinate system based on the recommended function curve of the zero-knowledge encoding constraint; converting the first parameter distribution matrix into a first parameter distribution grid; Coinciding a corner of the first parameter distribution grid with the origin of the two-dimensional grid coordinate system, coinciding two sides of the first parameter distribution grid with two axes of the two-dimensional grid coordinate system, and obtaining an online distribution parameter value set, wherein the online distribution parameter value set has an online distribution coordinate set; Based on the online distribution coordinate set, the offline distribution parameter value set is encoded in combination with the offline distribution coordinate set to obtain the zero-knowledge encoding result; The step of encoding the online distribution parameter value set based on the online distribution coordinate set and in combination with the offline distribution coordinate set to obtain the zero-knowledge encoding result includes: According to the online distribution coordinate set, extracting the first online distribution coordinates until the Mth online distribution coordinates; Partition the offline distribution coordinate set according to the first online distribution coordinates to the Mth online distribution coordinates to obtain a first online distribution and offline distribution coordinate matching set to an Mth online distribution and offline distribution coordinate matching set; Taking the first online distribution coordinates as a reference, traversing the first online distribution and offline distribution coordinate matching sets to perform coordinate deviation encoding, and obtaining a coordinate deviation binary vector set; Based on the first online distribution coordinate parameter value, traverse the first online distribution and offline distribution coordinate matching parameter value set to perform deviation encoding, and obtain a parameter value deviation unary vector set; Combining the one-to-one corresponding coordinate deviation binary vector set and the parameter value deviation one-element vector set to construct a first line distribution coordinate body three-element array set; Constructing a first online distribution coordinate header ternary array using the first online distribution coordinates and the first online distribution coordinate parameter values; Constructing a first online distributed coordinate zero-knowledge encoding result according to the first online distributed coordinate header ternary array and the first online distributed coordinate body ternary array set; Until the zero-knowledge coding result of the distribution coordinates on the Mth line is constructed; Add the zero-knowledge encoding results of the distribution coordinates on the first line to the zero-knowledge encoding results of the distribution coordinates on the Mth line into the zero-knowledge encoding results; Partitioning the offline distribution coordinate set according to the first online distribution coordinates to the M-th online distribution coordinates to obtain the first online distribution and offline distribution coordinate matching sets to the M-th online distribution and offline distribution coordinate matching sets includes: Taking the first online distribution coordinates to the Mth online distribution coordinates as center coordinates, partitioning the offline distribution coordinate set to obtain a partition result; When the area variance of the partitioning result is less than or equal to the variance threshold, obtaining the first online distribution and offline distribution coordinate matching set until the Mth online distribution and offline distribution coordinate matching set; The step of sending the zero-knowledge encoding result to the cloud server for decoding and storage includes: On the cloud server, decoding the zero-knowledge encoding result according to the encoding constraint to obtain the air separation unit control parameter and the air separation unit state parameter; Performing state prediction according to the air separation unit control parameters to obtain standard state parameters of the air separation unit; Comparing the standard state parameter of the air separation unit with the state parameter of the air separation unit to obtain a state deviation vector of the air separation unit; Performing abnormal identification on the state parameter of the air separation unit according to the state deviation vector of the air separation unit to obtain an abnormal identification result; storing the abnormal identification result, the air separation unit control parameter and the air separation unit state parameter; Wherein, performing state prediction according to the control parameters of the air separation unit to obtain the standard state parameters of the air separation unit includes: According to the model of air separation unit, collect the control parameter record data of air separation unit and the standard state record parameters of air separation unit; Using the control parameter record data of the air separation unit and the standard state record parameters of the air separation unit, a state prediction model of the air separation unit is configured, and the state prediction model of the air separation unit is embedded in the cloud server; The air separation unit control parameters are processed according to the air separation unit state prediction model to obtain the air separation unit standard state parameters.

2. The method according to claim 1, characterized in that When the air separation device control parameter and the air separation device state parameter are received, requesting the cloud server to download the coding constraint and obtaining the cloud server feedback information, further comprising: When requesting to download the coding constraint from the cloud server, performing coding constraint optimization on the cloud server, obtaining the zero-knowledge coding constraint, and adding it to the feedback information of the cloud server; The cloud server feedback information is received from the cloud server.

3. The method according to claim 2, characterized in that Performing coding constraint optimization on the cloud server to obtain zero-knowledge coding constraints includes: Get the function curve library; According to the position number of the air separation unit, a set of historical selection function curves is obtained; Construct the function curve using the fitness function: ； ； in, Characterize the i-th function curve of the function curve library, The jth function curve representing the set of historically selected function curves, Characterizes the fitness of the i-th function curve, Characterize the weight of the jth function curve, represents the time interval from the last time the jth function curve was selected to the current time, N represents the number of historically selected function curve sets, Characterize the distribution distance between the i-th function curve and the j-th function curve, and the distribution distance is characterized by the closed figure area of ​​the curve; Based on the historically selected function curve set, the function curve library is optimized in combination with the function curve selection fitness function to obtain a recommended function curve; The recommendation function curve is set as the zero-knowledge encoding constraint.

Images