Mechanical equipment remote monitoring and maintenance method based on Internet of Things

Abstract

The invention discloses a mechanical equipment remote monitoring and maintenance method based on the Internet of Things, and belongs to the technical field of mechanical equipment monitoring and maintenance. Comprising the steps that multiple types of sensors are installed at key parts of equipment, a Wi-Fi or 4G / 5G communication module and an MQTT or CoAP protocol are adapted, and a data acquisition system is constructed. And then collecting historical data of the equipment, after standardization processing, selecting an SVM model and kernel function training according to data characteristics so as to judge the equipment state in the real-time data and perform early warning. When the equipment is normal, the particle swarm optimization algorithm determines parameters according to production requirements, and constructs a fitness function to iteratively optimize the performance. And finally, packaging related data JSON into blocks by using an Ethereum or hyperledger block chain, thereby realizing maintenance record tracing and intelligent contract authority management, and ensuring data security. According to the invention, traditional maintenance defects are effectively overcome, real-time equipment monitoring, performance improvement and data security management are realized, and stable and efficient operation of industrial production is powerfully promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment monitoring and maintenance, and in particular to a mechanical equipment remote monitoring and maintenance method based on the Internet of Things. Background Art

[0002] In modern industrial production, the stable operation of mechanical equipment is of vital importance. Traditional equipment maintenance methods mostly rely on manual inspections and regular maintenance, which has many disadvantages. On the one hand, manual inspections are difficult to achieve real-time and continuous monitoring, and can often only be processed after the equipment shows obvious signs of failure, which may lead to extended equipment downtime, production interruptions, and huge economic losses to the company. On the other hand, the recording and analysis of equipment operation data lacks systematicity and accuracy, making it difficult to extract valuable information from large amounts of data to guide equipment maintenance and performance optimization.

[0003] With the rapid development of Internet of Things technology, the interconnection of equipment has become possible, providing a technical basis for the real-time collection and remote transmission of equipment data. At the same time, machine learning algorithms such as SVM have shown strong capabilities in data classification and prediction, and can effectively handle the problem of judging the operating status of equipment. The particle swarm optimization algorithm has significant advantages in the field of equipment performance optimization, and can find the optimal operating parameters according to the operating characteristics and production needs of the equipment. The emergence of blockchain technology provides a reliable solution for the secure storage and management of equipment data, the trusted traceability of maintenance records, and the fine control of permissions. Summary of the invention

[0004] The purpose of the present invention is to provide a remote monitoring and maintenance method for mechanical equipment based on the Internet of Things to solve the problems of low efficiency, poor accuracy and insufficient data security in the maintenance of traditional mechanical equipment.

[0005] To achieve the above object, the present invention provides a remote monitoring and maintenance method for mechanical equipment based on the Internet of Things, comprising the following steps:

[0006] S1. Infrastructure construction and data collection: By installing various sensors at key parts of mechanical equipment, a comprehensive data collection system is built to monitor the equipment's operating status and working environment in real time, and the sensors are configured with appropriate IoT communication modules and communication protocols;

[0007] S2, SVM-driven equipment status monitoring: Collect historical data of equipment in normal and faulty states, and standardize the data. Select appropriate SVM models and kernel functions for training and obtain model parameters; input newly collected real-time data into the trained SVM model after preprocessing, judge the equipment status, and issue warnings for abnormal conditions in a timely manner;

[0008] S3, particle swarm optimization to improve equipment performance: start the particle swarm optimization algorithm, randomly initialize the position and speed of the particle swarm according to the operating parameters to be optimized in step S2, build a fitness function based on the equipment performance indicators, and balance the optimization objectives by adjusting the weight coefficients;

[0009] S4. Data security management: Package SVM training data, model parameters, equipment operation data, particle swarm optimization process data and maintenance records into blocks in JSON format, use blockchain to trace maintenance records, define different role operation permissions through smart contracts, and ensure system security and data confidentiality.

[0010] Preferably, in step S1, an adapted IoT communication module is connected to each sensor, and Wi-Fi or 4G / 5G is selected as the communication mode according to the environment in which the device is located and the data transmission requirements, and the corresponding communication protocol is configured, and MQTT or CoAP is selected.

[0011] Preferably, in step S2, historical data of the device in normal and fault states are collected and divided into a training set and a test set according to a certain ratio;

[0012] Standardize the data to eliminate the impact of dimension;

[0013] According to the linear separability of the data, select the appropriate SVM model and kernel function for training. If the equipment operation data is linearly separable, use the linear SVM model to solve it; if it is nonlinearly separable, introduce the radial basis kernel function RBF to solve and obtain the model parameters;

[0014] The newly collected real-time data is preprocessed in the same way and then input into the trained SVM model to determine the equipment status.

[0015] Preferably, in step S3, the goal of particle swarm optimization is clarified according to the production requirements and performance indicators of the equipment, and the equipment operating parameters that need to be optimized are determined;

[0016] According to the number of parameters to be optimized, the dimension of the particles is determined, and the position and velocity of the particle swarm are randomly initialized;

[0017] Construct a fitness function based on the optimization goal;

[0018] Each particle is updated according to its own historical optimal position and the historical optimal position of the group according to its speed and position;

[0019] The particle update process is repeated continuously. Each iteration calculates the fitness value of each particle and updates the historical optimal position of the particle and the historical optimal position of the group.

[0020] When the termination condition is met, the iteration process ends. At this time, the equipment operating parameters corresponding to the historical optimal position of the group are the optimized parameters.

[0021] Preferably, in step S4, the blockchain platform selects Ethereum or Hyperledger to build a blockchain node, configures the parameters of the blockchain node according to actual needs, initializes the smart contract development environment of the blockchain, and installs related development tools and libraries.

[0022] Preferably, in step S4, the SVM training data, model parameters, equipment operation data, particle swarm optimization process data and maintenance records are organized into a specific JSON structure using JSON format;

[0023] The formatted data is packaged according to the block structure requirements of the blockchain. Each block contains the hash value of the previous block, timestamp, data, and the hash value of the current block. The hash value of the current block is calculated using SHA-256 to ensure the integrity and non-tamperability of the data.

[0024] Preferably, in step S4, the packaged blocks are linked into a blockchain in chronological order and stored on distributed nodes. Each node saves a complete copy of the blockchain. The consistency of the data of each node is ensured through the consensus mechanism of the blockchain. The blockchain data is backed up regularly to prevent data loss. At the same time, a data recovery mechanism is established.

[0025] Therefore, the present invention adopts a mechanical equipment remote monitoring and maintenance method based on the Internet of Things with the above structure, which has the following beneficial effects:

[0026] (1) It realizes real-time remote monitoring of mechanical equipment, which can promptly detect hidden dangers of equipment failure, significantly reduce equipment downtime, improve production efficiency, and reduce economic losses caused by equipment failure.

[0027] (2) With the help of advanced machine learning algorithms and optimization algorithms, it is possible to intelligently optimize equipment performance, improve equipment operating performance, reduce energy consumption, improve product quality, and enhance the company's market competitiveness.

[0028] (3) Use blockchain technology to ensure data security and management standards, ensure the integrity, immutability and traceability of device data, effectively protect the company's core data and intellectual property rights, and at the same time achieve sophisticated permission management through smart contracts to improve the security and reliability of the system.

[0029] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1The present invention is a flowchart of a method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things. DETAILED DESCRIPTION

[0031] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0032] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0033] Example

[0034] like Figure 1 As shown, the present invention provides a remote monitoring and maintenance method for mechanical equipment based on the Internet of Things, which is specifically as follows:

[0035] S1. Basic construction and data collection: Various sensors, including temperature sensors, vibration sensors, pressure sensors, speed sensors, etc., are carefully installed at key parts of mechanical equipment, such as engine bearings, gears of transmission systems, key nodes of hydraulic systems, etc. At the same time, temperature and humidity sensors and air quality sensors are arranged in the surrounding environment of the equipment, so as to build a comprehensive and multi-dimensional data collection system. These sensors can capture the operating status information and working environment parameters of the equipment in real time and convert them into electrical signals or digital signals. To ensure stable and efficient data transmission, an adapted IoT communication module is connected to each sensor according to the network coverage and data transmission requirements of the environment where the equipment is located. In indoor workshop environments with good network conditions, Wi-Fi communication modules are preferred; in the wild or places where network signals are unstable, 4G / 5G communication modules are used. At the same time, corresponding communication protocols, such as MQTT or CoAP, are configured to transmit the collected data to the data center in real time according to predetermined rules, providing a rich and accurate data basis for subsequent analysis and processing.

[0036] S2, SVM-driven equipment status monitoring: extensively collect historical data of equipment in normal operation and various fault conditions, which covers raw data collected by sensors, equipment operation logs, previous fault diagnosis reports and other information. Strictly screen and organize the collected data, remove duplicate, erroneous or obviously abnormal data, and use 70%-80% as training set and 20%-30% as test set;

[0037] The standardized formula is used to standardize the data, effectively eliminating the dimensional differences between different features.

[0038] The normalization formula is:

[0039] If the equipment operation data is judged to present linearly separable characteristics through data analysis, the linear SVM model is adopted to determine the model parameters by solving the optimization problem.

[0040] If the data is nonlinearly separable, the radial basis kernel function is introduced to map the data into a high-dimensional space and then solve the optimization problem.

[0041] During the operation of the equipment, the newly collected real-time data undergoes the same preprocessing steps as the training set and is then input into the trained SVM model to determine the equipment status.

[0042] Once it is determined that the equipment is in an abnormal state, an early warning is immediately issued to relevant maintenance personnel through various means (such as SMS notifications, system pop-up alarms, email reminders, etc.) so that countermeasures can be taken quickly.

[0043] S3. Particle swarm optimization to improve equipment performance: When the equipment is determined to be in normal operation by SVM, the particle swarm optimization algorithm is started to further improve the equipment performance.

[0044] According to the production process requirements and performance improvement goals of the equipment, we take improving production efficiency while reducing energy consumption as an example, and accurately determine the equipment operating parameters that need to be optimized. Here, we select the motor speed range and the feed setting value of the processing technology to determine the dimension of the particles. If only the motor speed and processing feed are optimized, the dimension of the particles is 2. Then, the position and speed of the particle swarm are randomly initialized within the reasonable range of the parameters. The position represents a possible combination of a set of equipment operating parameters, and the speed determines the movement direction and step size of the particles in the search space.

[0045] Determine the optimization goal, which is to reduce energy consumption while improving production efficiency, and construct a fitness function:

[0046]

[0047] Among them, α and β are weight coefficients, which are flexibly adjusted according to actual production needs to balance the relative importance of production efficiency and energy consumption in the optimization process.

[0048] During the operation of the algorithm, each particle iteratively updates its speed and position based on its own historical optimal position and the historical optimal position of the group.

[0049] Each iteration recalculates the fitness value of each particle, and promptly updates the historical optimal position of the particle and the historical optimal position of the group. When the predetermined termination conditions are met (such as reaching the set maximum number of iterations, the fitness function value converges to a certain accuracy range, etc.), the iteration process ends, and the device operating parameters corresponding to the historical optimal position of the group are the optimized parameters. These optimized parameters are sent to the control system of the device to achieve automatic adjustment of the device operating status, thereby significantly improving the performance of the device.

[0050] S4. Data security management: Choose mature blockchain platforms such as Ethereum or Hyperledger to build blockchain nodes. According to actual application scenarios and security requirements, reasonably configure various parameters of blockchain nodes, including Ethereum's PoW, PoS or Hyperledger's PBFT;

[0051] At the same time, initialize the smart contract development environment of the blockchain, install relevant development tools and libraries, and lay the foundation for the subsequent data storage and permission management functions. Using JSON format, carefully organize various types of data such as SVM training data, model parameters, equipment operation data, particle swarm optimization process data, and maintenance records to form a JSON data block with a clear structure and easy to parse. According to the block structure specification requirements of the blockchain, the formatted data is packaged. Each block contains the hash value of the previous block, an accurate timestamp, data content, and the hash value of this block. The hash value of this block is calculated by hash algorithms such as SHA-256 to ensure the integrity and non-tamperability of the data during storage and transmission. The packaged blocks are linked into a blockchain in chronological order and stored on distributed nodes. Each node saves a complete copy of the blockchain.

[0052] With the help of the consensus mechanism of blockchain, the consistency and integrity of the data of each node are guaranteed, effectively preventing the data from being maliciously tampered with or lost. Blockchain data is backed up regularly, and a complete data recovery mechanism is established to ensure that data can be quickly restored in the event of unexpected situations (such as node failure, data corruption, etc.), ensuring the continuous and stable operation of the system. The traceability of blockchain is used to achieve the detailed traceability function of maintenance records, and the operation permissions of different roles are accurately defined through the developed smart contracts to ensure that only authorized personnel can access and operate the corresponding data within the prescribed scope of authority, effectively ensuring system security and data confidentiality.

[0053] Therefore, the present invention adopts the above-mentioned remote monitoring and maintenance method of mechanical equipment based on the Internet of Things, collects equipment operation data and environmental data through sensors, and uses the Internet of Things technology to realize remote transmission of data. The SVM algorithm is based on the historical data training model, classifies the real-time data to judge the equipment status, and realizes early warning of faults. When the equipment is operating normally, the particle swarm optimization algorithm improves the equipment performance by continuously iteratively searching for the optimal operating parameters. Blockchain technology ensures the data security and credibility of the entire system from aspects such as data storage, maintenance record tracing and authority management. The three work together to form a complete remote monitoring and maintenance system for mechanical equipment, effectively improving the reliability, operation efficiency and maintenance management level of the equipment, reducing the equipment failure rate and maintenance cost, and providing strong support for the stable operation of industrial production.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A remote monitoring and maintenance method for mechanical equipment based on the Internet of Things, characterized in that: The following steps are involved: S1. Infrastructure construction and data collection: By installing various sensors at key parts of mechanical equipment, a comprehensive data collection system is built to monitor the equipment's operating status and working environment in real time, and the sensors are configured with appropriate IoT communication modules and communication protocols; S2, SVM-driven equipment status monitoring: Collect historical data of equipment in normal and faulty states, and standardize the data. Select appropriate SVM models and kernel functions for training and obtain model parameters; input newly collected real-time data into the trained SVM model after preprocessing, judge the equipment status, and issue warnings for abnormal conditions in a timely manner; S3, particle swarm optimization to improve equipment performance: start the particle swarm optimization algorithm, randomly initialize the position and speed of the particle swarm according to the operating parameters to be optimized in step S2, build a fitness function based on the equipment performance indicators, and balance the optimization objectives by adjusting the weight coefficients; S4. Data security management: Package SVM training data, model parameters, equipment operation data, particle swarm optimization process data and maintenance records into blocks in JSON format, use blockchain to trace maintenance records, define different role operation permissions through smart contracts, and ensure system security and data confidentiality.

2. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1, characterized in that: In step S1, connect an adapted IoT communication module to each sensor. According to the device environment and data transmission requirements, select Wi-Fi or 4G / 5G as the communication mode, and configure the corresponding communication protocol, such as MQTT or CoAP.

3. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1 is characterized in that: In step S2, historical data of the equipment in normal and fault states are collected and divided into a training set and a test set according to a certain ratio; Standardize the data to eliminate the impact of dimension; According to the linear separability of the data, select the appropriate SVM model and kernel function for training. If the equipment operation data is linearly separable, use the linear SVM model to solve it; if it is nonlinearly separable, introduce the radial basis kernel function RBF to solve and obtain the model parameters; The newly collected real-time data is preprocessed in the same way and then input into the trained SVM model to determine the equipment status.

4. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1 is characterized in that: In step S3, according to the production requirements and performance indicators of the equipment, the goal of particle swarm optimization is clarified, and the equipment operating parameters that need to be optimized are determined; According to the number of parameters to be optimized, the dimension of the particles is determined, and the position and velocity of the particle swarm are randomly initialized; Construct a fitness function based on the optimization goal; Each particle is updated according to its own historical optimal position and the historical optimal position of the group according to its speed and position; The particle update process is repeated continuously. Each iteration calculates the fitness value of each particle and updates the historical optimal position of the particle and the historical optimal position of the group. When the termination condition is met, the iteration process ends. At this time, the equipment operating parameters corresponding to the historical optimal position of the group are the optimized parameters.

5. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1 is characterized in that: In step S4, the blockchain platform selects Ethereum or Hyperledger to build a blockchain node, configures the parameters of the blockchain node according to actual needs, initializes the blockchain's smart contract development environment, and installs related development tools and libraries.

6. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1 is characterized in that: In step S4, the SVM training data, model parameters, equipment operation data, particle swarm optimization process data, and maintenance records are organized into a specific JSON structure using the JSON format; The formatted data is packaged according to the block structure requirements of the blockchain. Each block contains the hash value of the previous block, timestamp, data, and the hash value of the current block. The hash value of the current block is calculated using SHA-256 to ensure the integrity and non-tamperability of the data.

7. The method for remote monitoring and maintenance of mechanical equipment based on the Internet of Things according to claim 1 is characterized in that: In step S4, the packaged blocks are linked into a blockchain in chronological order and stored on distributed nodes. Each node saves a complete copy of the blockchain. The consensus mechanism of the blockchain is used to ensure the consistency of data on each node. The blockchain data is backed up regularly to prevent data loss. At the same time, a data recovery mechanism is established.

Images