Nickel processing remote control and monitoring system

Abstract

The invention discloses a nickel processing remote control and monitoring system, and particularly relates to the technical field of nickel processing equipment, which comprises a data acquisition module, a data transmission module, a data processing and analysis module, a remote control module, a visual monitoring module and a system management module, wherein the data acquisition module is used for acquiring data such as temperature, pressure and components from a nickel processing equipment sensor and the like; the data transmission module encodes and encrypts the original data and transmits the original data to a processing end in a wired or wireless manner; the data processing and analyzing module is used for preprocessing data, extracting screening features and training a model by using an algorithm; the remote control module is used for setting authority management and supporting manual and automatic control of equipment parameters; the visual monitoring module is used for displaying real-time and historical data through charts and processes; the accuracy of data acquisition is improved to 99% or above through the data acquisition module by utilizing various high-precision sensors and a multi-source data fusion algorithm, and the continuity of data acquisition is guaranteed by matching with an 8-16-hour data caching technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of nickel processing equipment, more particularly, the present application relates to a kind of nickel processing remote control and monitoring system. BACKGROUND

[0002] The core technical bottleneck of the existing remote control and monitoring system is the lack of precision and real-time performance in data acquisition and processing. The sensors used in traditional systems have low precision (e.g., temperature sensor error ±2℃, pressure sensor error ±3%FS), and lack a multi-source data fusion mechanism, making it difficult to accurately capture the dynamic coupling relationship of parameters such as temperature, pressure, and component concentration during nickel smelting (e.g., the real-time correlation between nickel ion concentration and electrolytic voltage in the electrolytic cell). At the same time, data processing relies on simple filtering and manual experience analysis, resulting in a delay of more than 2 hours in adjusting key process parameters (such as smelting furnace temperature control threshold), causing the purity of nickel products to fluctuate by ±0.5%, and the waste rate to reach 12%. In addition, the data caching capability is weak (only supporting 10 minutes of offline caching), and the loss rate of key production data exceeds 30% when the network is abnormal, seriously affecting the accuracy of process tracing and fault analysis, and restricting the intelligent control level of nickel processing production. To overcome these problems, a nickel processing remote control and monitoring system is proposed. SUMMARY

[0003] To overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a nickel processing remote control and monitoring system, which uses a variety of high-precision sensors and multi-source data fusion algorithms to improve the accuracy of data acquisition to more than 99% through the data acquisition module, and cooperates with 8-16 hours of data caching technology to ensure the continuity of data acquisition; the data transmission module uses AES-256 encryption and RS error correction coding to reduce the data transmission error rate to below 0.01%, and combines a hybrid communication network to ensure stable data transmission; the data processing and analysis module uses algorithms such as median filtering and principal component analysis to improve the data processing efficiency by 40%, and the model prediction accuracy reaches 85%, providing a reliable basis for process optimization.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a nickel processing remote control and monitoring system, comprising a data acquisition module, a data transmission module, a data processing and analysis module, a remote control module, a visual monitoring module, and a system management module, wherein: The data acquisition module acquires temperature, pressure, and component data from nickel processing equipment sensors; The data transmission module encodes and encrypts the original data and transmits it to the processing end through wired and wireless transmission; The data processing and analysis module preprocesses the data, extracts and filters features, and trains the model using algorithms; Remote control module: set permission management, support manual, automatic control device parameters; Visualization monitoring module: real-time and historical data are displayed in charts and processes. System management module: manage device information, user accounts and system configuration.

[0005] In a preferred embodiment: the data acquisition module uses high-precision sensors deployed in the nickel processing equipment location, high-precision sensors include: using thermocouple sensors to collect temperature data of smelting furnaces and reaction kettles; using pressure transmitters to obtain the pressure inside the pipelines and storage tanks, at the same time, using component analyzers to monitor the nickel and impurity content in nickel ore, solution and finished products; using multi-source data fusion algorithm to integrate heterogeneous data collected by different sensors to ensure the accuracy and integrity of the data, and using data caching technology to cache 8-16 hours of data when there is a temporary network failure, ensuring the continuity of data acquisition.

[0006] In a preferred embodiment: the data transmission module uses AES-256 encryption algorithm to encrypt the original data, and uses RS error correction coding to enhance the anti-interference ability; using low-power Wi-Fi technology based on IEEE 802.11ah standard inside the workshop to aggregate short-distance sensor data at a rate of not less than 10Mbps; using 5G network slicing technology and industrial-grade optical fiber to transmit data to the data processing end at a rate of 100Mbps.

[0007] In a preferred embodiment: the data processing and analysis module uses median filter algorithm for denoising, uses Min-Max normalization method to unify the dimension of numerical data; uses principal component analysis algorithm to extract key features, and the dimension of the data after feature selection is reduced to 30% of the original data; uses random forest algorithm and long short-term memory network to train the model based on Python language Scikit-learn and TensorFlow framework, and optimizes the hyperparameters through 5-fold cross-validation to make the model prediction accuracy reach 85%.

[0008] In a preferred embodiment: the remote control module builds a role-based access control permission management system, sets administrator, engineer and operator roles, and uses username and password and SMS verification code two-factor authentication for user login; in manual control mode, users use PC-side application programs developed based on Java language and mobile-side APPs developed based on ReactNative to remotely control the start and stop of electric valves and motor equipment and adjust parameters according to real-time monitoring data; in automatic control mode, the system automatically calls control instruction interfaces to adjust device parameters according to rule scripts written based on Drools rule engine.

[0009] In a preferred embodiment: the visual monitoring module adopts HTML5, CSS3 and JavaScript technology, uses ECharts visualization library to dynamically display temperature, pressure, component content and other parameters in line chart and column chart, the time interval is 1 minute, the process flow is presented in flow chart, the device running state is updated in real time, the delay time is less than or equal to 1 second, the user can retrieve historical data within 3 years according to time range and device name conditions from the HBase distributed database through SQL query statement, and generate historical report, which supports CSV and Excel format export.

[0010] In a preferred embodiment: the system management module uses Zabbix device management software to monitor hardware devices, collects device CPU usage, memory occupancy and other performance indicators every 5 minutes; records device model, manufacturer, installation location, purchase time, warranty period and other information through CMDB; manages user accounts using a user management system developed based on SpringSecurity, and records user login time, operation content, operation result and other information using a Log4j log management system, retains logs for 2 years, and updates system software version every quarter using Ansible automation deployment tool.

[0011] Technical effects and advantages of the application: the data acquisition module uses multiple high-precision sensors and multi-source data fusion algorithms to improve the accuracy of data acquisition to more than 99%, and cooperates with 8-16 hour data caching technology to ensure data acquisition continuity; the data transmission module uses AES-256 encryption and RS error correction coding to reduce data transmission error rate to below 0.01%, and combines hybrid communication network to ensure stable data transmission; the data processing and analysis module uses median filtering, principal component analysis and other algorithms to improve data processing efficiency by 40%, model prediction accuracy reaches 85%, and provides reliable basis for process optimization. The permission management and dual-mode control of the remote control module improve the safety of device operation by 60%, and shorten the control response time to within 500ms; the visual monitoring module realizes 1-minute interval real-time data display and 3-year historical data fast query, and the production state presentation efficiency is improved by 50%; the system management module improves device maintenance efficiency by 30% through Zabbix, CMDB and other tools, and significantly enhances the standardization of user management, and the modules work collaboratively to realize efficient monitoring, precise control and intelligent management of the nickel processing production process, effectively improve production efficiency and product quality, and reduce operating costs and safety risks. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 The schematic diagram of the working system module of the application is shown. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0014] Example embodiments will now be described more fully with reference to the accompanying drawings. A nickel processing remote control and monitoring system includes a data acquisition module, a data transmission module, a data processing and analysis module, a remote control module, a visual monitoring module, and a system management module, wherein: Data acquisition module: collects temperature, pressure, composition and other data from nickel processing equipment sensors; Data transmission module: encodes and encrypts the original data and transmits it to the processing end via wired or wireless transmission; Data processing and analysis module: preprocess data, extract and filter features, and train models using algorithms; Remote control module: set authority management and support manual and automatic control of device parameters; Visual monitoring module: displays real-time and historical data in charts and processes; System management module: manages equipment information, user accounts, and system configurations; the data acquisition module uses high-precision sensors deployed at the nickel processing equipment location. High-precision sensors include: using thermocouple sensors to collect temperature data from smelting furnaces and reactors; using pressure transmitters to obtain pressure in pipelines and storage tanks; and using component analyzers to monitor the nickel and impurity content in nickel ore, solutions, and finished products; using multi-source data fusion algorithms to integrate heterogeneous data collected by different sensors to ensure data accuracy and integrity. Combined with data caching technology, 8-16 hours of data can be cached in the event of a temporary network failure to ensure the continuity of data collection; using a weighted average fusion algorithm to fuse heterogeneous data collected by different types of sensors. For multiple sensor data of the same physical quantity, weights are assigned based on the accuracy and reliability of the sensors. The calculation formula is: ,in, is the fused data value, For the The measured values ​​of the sensors, For the The weights of the sensors, and satisfy Weight Based on the historical measurement error of the sensor Dynamic calculation: .

[0015] The data transmission module uses AES-256 encryption algorithm to encrypt the original data, and uses RS error correction coding to enhance the anti-interference capability; through the low-power Wi-Fi technology based on IEEE802.11ah standard in the workshop, the short-distance sensor data is aggregated at a rate of not less than 10Mbps; with the help of 5G network slicing technology and industrial-grade optical fiber, the data is stably transmitted to the data processing end at a rate of 100Mbps; AES-256 encryption algorithm: using advanced encryption standard (AES), the key length is 256 bits, and the encryption block size is 128 bits. The encryption process includes initial round, 9 standard rounds and 1 final round, each round contains four operations of byte substitution, row shift, column mixing and round key addition; the encryption formula is: wherein, is the plaintext, is the ciphertext, is the 256-bit key, is the encryption function; RS(255,223) error correction coding: using Reed-Solomon code, which can correct up to 16 bytes of error. The coding efficiency is 223 / 255 ; the coding formula is: wherein, is the information polynomial (223 bytes), is the check polynomial (32 bytes), .

[0016] The data processing and analysis module uses median filtering algorithm for denoising, and uses Min-Max normalization method to unify the dimension of numerical data; the key features are extracted by using principal component analysis algorithm, and the data dimension after feature selection is reduced to 30% of the original data; based on Python language Scikit-learn and TensorFlow framework, random forest algorithm and long short-term memory network are used to train the model, and the model prediction accuracy reaches 85% through 5-fold cross-validation optimization of hyperparameters; median filtering algorithm: sort the data in the sliding window with length , and take the middle value as the filtering result; the calculation formula is: wherein, is the original data, is the filtered data, and the window size ; Min-Max ; feature extraction and selection: principal component analysis (PCA): by calculating the eigenvalues and eigenvectors of the covariance matrix of the data, the original data is projected into a low-dimensional space. Let the original data matrix be , then the covariance matrix is: , and the eigenvalues and the corresponding eigenvectors are obtained by eigenvalue decomposition of , and the first The eigenvector corresponding to the maximum eigenvalue constitutes a projection matrix The data after dimension reduction is: , wherein, That is, the data dimension is reduced to 30% of the original data; Random forest algorithm: composed of 100 decision trees, the training samples of each tree are randomly extracted from the original data by bootstrap sampling method, and the Gini impurity is used as the splitting standard for feature selection. For classification problems, the output of random forest is the majority voting result of all decision trees; for regression problems, the output is the average value of all decision tree outputs.

[0017] Long short-term memory network (LSTM): the number of hidden layer neurons is 128, the input sequence length is 60 (corresponding to 1 hour of data), and the output dimension is 1. The calculation formula of the LSTM unit is: , wherein, are the input gate, the forget gate and the output gate, respectively, is the unit state, is the hidden state, is the sigmoid function, is the element-wise multiplication.

[0018] 5-fold cross-validation: the data set is divided into 5 subsets, and 4 subsets are used each time.

[0019] The remote control module builds a role-based access control permission management system, sets administrator, engineer, operator roles, and uses username password and SMS verification code two-factor authentication for user login. In manual control mode, users control the start and stop of electric valves and motor equipment and parameter adjustment through PC-side application programs developed based on Java language and mobile-side APP developed based on ReactNative, according to real-time monitoring data. In automatic control mode, the system automatically calls control instruction interface to adjust equipment parameters according to the rule script written based on Drools rule engine. Role-based access control (RBAC): define three roles of administrator, engineer and operator, which have different permissions such as system configuration, parameter adjustment and equipment operation. The mapping relationship between roles and permissions is stored in a relational database, and is realized by using a many-to-many association table; Two-factor authentication: when logging in, the user needs to enter the username and password, and the system sends a 6-digit verification code to the user's bound mobile phone, which needs to be entered by the user for secondary verification; The verification code is valid for 30 seconds, and is generated by using HMAC-SHA256 algorithm; The visual monitoring module uses HTML5, CSS3 and JavaScript technology, uses ECharts visualization library to display temperature, pressure, component content and other parameters with dynamic line chart and column chart, time interval is 1 minute, process flow is presented with flow chart, equipment running state is updated in real time, delay time is less than or equal to 1 second, users can retrieve historical data within 3 years according to time range and equipment name conditions from HBase distributed database through SQL query statement, and generate historical report, support export in CSV and Excel format; dynamic line chart: realized by using ECharts library, X axis is time (time interval is 1 minute), Y axis is temperature, pressure, component content and other parameters. The chart supports scaling, panning, data point query and other functions, data update frequency is 1 second / time, process flow chart: drawn using SVG technology, equipment state (running, pause, fault) is identified by different colors, real-time update delay time is less than or equal to 1 second. When the equipment state is switched, animation effect is added to enhance visual feedback.

[0020] The system management module uses Zabbix device management software to monitor hardware devices, collects device CPU usage, memory occupancy and other performance indicators every 5 minutes; records device model, manufacturer, installation location, purchase time, warranty period and other information through CMDB; uses the user management system developed based on SpringSecurity to manage user accounts, uses Log4j log management system to record user login time, operation content, operation result and other information, retains logs for 2 years, uses Ansible automation deployment tool to update system software version every quarter; Zabbix device management software: collects device CPU usage, memory occupancy, disk I / O and other performance indicators every 5 minutes, the collection script is written in Python, and device information is obtained through SNMP protocol. Performance threshold setting: when CPU usage exceeds 80% and memory occupancy exceeds 90%, the system automatically sends warning email to administrator mailbox.

[0021] The above-described embodiments can be implemented, wholly or partially, by software, hardware, firmware, and any combination thereof. When implemented by software, the above-described embodiments can be implemented, wholly or partially, in the form of a computer program product. The computer program product includes one or more computer instructions and computer programs. When the computer instructions and computer programs are loaded and executed on a computer, the processes and functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, and data center to another website, computer, server, and data center through a wired (for example, infrared, wireless, microwave) manner. The computer-readable storage medium can be any available medium accessible by a computer or a server, data center data storage device containing one or a collection of available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0022] It should be understood that, in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0023] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0024] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0025] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0026] If the functions are implemented in the form of software function units and sold and used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0027] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes and replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A nickel processing remote control and monitoring system, characterized in that: It includes data acquisition module, data transmission module, data processing and analysis module, remote control module, visual monitoring module, and system management module, among which: Data acquisition module: collects temperature, pressure, and composition data from nickel processing equipment sensors; Data transmission module: encodes and encrypts the original data and transmits it to the processing end via wired or wireless transmission; Data processing and analysis module: preprocess data, extract and filter features, and train models using algorithms; Remote control module: set authority management and support manual and automatic control of device parameters; Visual monitoring module: displays real-time and historical data in charts and processes; System management module: manage device information, user accounts and system configuration.

2. A nickel processing remote control and monitoring system according to claim 1, characterized in that: The data acquisition module uses high-precision sensors deployed at the nickel processing equipment. The high-precision sensors include: using thermocouple sensors to collect temperature data from smelting furnaces and reactors; using pressure transmitters to obtain pressure in pipelines and storage tanks; and using component analyzers to monitor the nickel and impurity content in nickel ore, solutions and finished products. Multi-source data fusion algorithms are used to integrate heterogeneous data collected by different sensors to ensure data accuracy and integrity. Combined with data caching technology, 8-16 hours of data can be cached in the event of a temporary network failure to ensure the continuity of data collection.

3. A nickel processing remote control and monitoring system according to claim 1, characterized in that: The data transmission module uses the AES-256 encryption algorithm to encrypt the original data and adopts RS error correction coding to enhance anti-interference capabilities; through the low-power Wi-Fi technology based on the IEEE802.11ah standard within the workshop, short-distance sensor data is aggregated at a rate of no less than 10Mbps; with the help of 5G network slicing technology and industrial-grade optical fiber, data is stably transmitted to the data processing end at a rate of 100Mbps.

4. A nickel processing remote control and monitoring system according to claim 1, characterized in that: The data processing and analysis module uses the median filtering algorithm for denoising and the Min-Max normalization method to unify the dimensions of numerical data; the principal component analysis algorithm is used to extract key features, and the data dimension after feature screening is reduced to 30% of the original data. Based on the Scikit-learn and TensorFlow frameworks in the Python language, the random forest algorithm and long short-term memory network are used to train the model, and the hyperparameters are optimized through 5-fold cross-validation, so that the model prediction accuracy reaches 85%.

5. The nickel processing remote control and monitoring system according to claim 1, characterized in that: The remote control module builds a role-based access control authority management system, sets administrator, engineer, and operator roles, and uses two-factor authentication of username and password and SMS verification code for user login. In manual control mode, users can remotely control the start and stop and parameter adjustment of electric valves and motor equipment based on real-time monitoring data through PC applications developed based on Java language and mobile apps developed based on ReactNative. In automatic control mode, the system automatically calls the control instruction interface to adjust equipment parameters based on rule scripts written based on the Drools rule engine.

6. A nickel processing remote control and monitoring system according to claim 1, characterized in that: The visual monitoring module adopts HTML5, CSS3 and JavaScript technologies, and uses the ECharts visualization library to display temperature, pressure, and component content parameters with dynamic line charts and bar charts with an interval of 1 minute. The process flow is presented with a flow chart, and the equipment operation status is updated in real time with a delay time of ≤1 second. Users can use SQL query statements to retrieve historical data within 3 years from the HBase distributed database according to time range and equipment name conditions, and generate historical reports, which can be exported in CSV and Excel formats.

7. The nickel processing remote control and monitoring system according to claim 1, characterized in that: The system management module uses Zabbix device management software to monitor hardware devices, collecting device CPU usage and memory occupancy performance indicators every 5 minutes; records device model, manufacturer, installation location, purchase time, and warranty period information through CMDB; uses a user management system developed based on SpringSecurity to manage user accounts, and uses the Log4j log management system to record user login time, operation content, and operation results information, retaining logs for 2 years; and uses the Ansible automated deployment tool to update the system software version once a quarter.

Images