Wireless transmission work meeting data communication access equipment monitoring system

Abstract

The invention discloses a wireless transmission work meeting data communication access equipment monitoring system, relates to the technical field of wireless equipment transmission, and mainly solves the problem of monitoring of data communication access equipment. The wireless transmission work meeting data communication access equipment monitoring system comprises a monitoring center, communication access equipment, a sensor, network communication equipment and a maintenance management platform, and an optimal communication path is searched through a main controller of the monitoring center by adopting a hybrid optimization algorithm; the network communication equipment monitoring system adopts an improved hybrid encryption algorithm and a hybrid compression algorithm to accelerate the transmission speed of a data communication network, and monitors the abnormality of the data communication network through a data communication abnormality algorithm model GoogleNet-Unet +, thereby greatly improving the transmission efficiency of the communication network, and protecting the environmental safety of the communication network.

Description

Technical Field

[0001] This invention relates to the field of wireless data transmission technology, and more specifically to a wireless data communication access device monitoring system for trade unions. Background Technology

[0002] In industrial applications, wired connections are currently the primary means of achieving various control functions. The use of wired networks, including various bus technologies and local area networks (LANs), has indeed brought convenience to people's production and lives, changing our lives and greatly promoting social development. Wired networks offer high speed, large data throughput, and strong reliability, making them an ideal choice for relatively fixed equipment, and they have indeed achieved satisfactory results in practical applications. However, the drawbacks of wired networks—such as cumbersome cabling, difficulty in troubleshooting line faults, the need for rewiring when relocating equipment, and the inability to move equipment freely—are becoming increasingly prominent.

[0003] Trade union data communication refers to the technologies and tools used by trade unions in network communication. Trade unions typically need to perform large-scale data transmission, file transfer, and data storage tasks. During data exchange, VPNs, network storage devices, remote desktops, network proxies, and cloud storage services are commonly used for data exchange and computation. Cloud storage services are a technology that hosts data, allowing trade unions to store data in the cloud and gain advanced access privileges. Trade union data communication needs to consider data confidentiality, security, and reliability. Using technologies such as VPNs, network storage devices, remote desktops, and cloud storage services can help trade unions complete data transmission tasks more easily and protect data from unauthorized access. Trade unions can remotely connect to their office computers to process data or files. This can be achieved through remote desktop protocols (such as TCP / IP). However, with the development of radio frequency technology and integrated circuit technology, wireless communication is becoming increasingly easier to implement, and data transmission speeds are getting faster, gradually reaching levels comparable to wired networks. More and more enterprises and organizations are using trade union data communication access devices for internal communication and collaboration. However, due to the large number and wide distribution of equipment, its management and maintenance are difficult, and the data communication process is complex. This presents technical drawbacks for implementing union data communication access and equipment monitoring, easily leading to equipment damage and malfunctions, which in turn affect work efficiency and quality. Therefore, improving union data communication capabilities, enhancing data information monitoring, and strengthening data security are urgent technical issues that need to be addressed. Summary of the Invention

[0004] To address the shortcomings of the aforementioned technologies, this invention discloses a wireless transmission trade union data communication access device monitoring system. The system utilizes a hybrid optimization algorithm to find the optimal communication path through the main controller in the monitoring center. An improved hybrid encryption and compression algorithm is employed by the network communication device monitoring system to accelerate data communication network transmission. The GoogleNet-Unet+ data communication anomaly algorithm model is used to monitor data communication network anomalies. This significantly improves communication network transmission efficiency, enhances trade union data processing capabilities, and effectively protects the security of the communication network environment.

[0005] To achieve the above-mentioned technical effects, the present invention adopts the following technical solution: A wireless data communication access device monitoring system for trade unions includes a monitoring center, communication access devices, sensors, network communication devices, and a maintenance and management platform. The monitoring center is used to monitor and manage communication access equipment. The monitoring center includes a main controller, a data center, and a management center. The main controller is used to adjust the working status of each device. The management center includes a communication access equipment monitoring system, a network communication equipment monitoring system, and a sensor monitoring system. The communication access equipment monitoring system is used to monitor the operating status of the devices, network connection status, transmission rate, and device load. The network communication equipment monitoring system uses an improved RSA and AES hybrid encryption algorithm to encrypt data and uses the GoogleNet-Unet+ data communication anomaly algorithm model to analyze data communication anomalies. Communication access equipment is used to implement network communication functions; Sensors are used to monitor equipment status and environmental parameters, and transmit the data to the monitoring center for processing and analysis. Network communication equipment is used to realize data transmission and communication connections. The maintenance management platform is used to realize remote management and maintenance of equipment. The maintenance management platform includes a remote maintenance module and an equipment configuration module. The remote maintenance module is used to detect and display the communication process of each communication access device. The remote maintenance module includes an intelligent routing matching unit, a data compression unit, a data caching unit, and a data fragmentation unit. The equipment configuration module is used to remotely modify the operating parameters of each device. The communication access device is connected to the monitoring center, the monitoring center is connected to the sensors, the monitoring center is connected to the network communication device, and the network communication device is connected to the maintenance and management platform.

[0006] As a further description of the above technical solution, the working process of the communication access equipment monitoring system is as follows: First, the monitoring system is reasonably designed and laid out according to the factors of equipment type, quantity and distribution. Then, the algorithm and model are selected according to the characteristics and data type of the monitored object. Then, the monitoring data is alarmed and fed back in real time. Abnormal situations are responded to and handled in a timely manner according to the priority and processing method of the alarm. Finally, corresponding management and maintenance plans are formulated according to the communication access equipment monitoring system and professional technical personnel are assigned to maintain and manage it.

[0007] As a further description of the above technical solution, the working process of the network communication equipment monitoring system is as follows: First, the network range, data type and requirements, transmission latency and reliability are analyzed according to the application scenario. Then, the network scale, transmission distance and node density are comprehensively monitored according to the star, ring, tree or mesh structure adopted. Next, the wireless technology and protocol are detected and analyzed according to the application scenario and network topology. Finally, the network communication equipment monitoring system is protected by data encryption and anomaly analysis.

[0008] As a further description of the above technical solution, the anomaly analysis method is as follows: Step 1: Detect network anomalies through statistical analysis, machine learning, and data mining; Step 2: Deeply mine and analyze abnormal data through data processing and data visualization; Step 3: Determine the specific location and cause of the anomaly through network topology analysis, route tracing, and port monitoring; Step 4: Repair the anomaly by using software repair, hardware replacement, and network topology adjustment, depending on the specific cause and location of the anomaly. Step 5: Real-time monitoring and management of network operation status through network topology monitoring, device status monitoring, and data traffic monitoring.

[0009] As a further description of the above technical solution, the data communication anomaly algorithm model includes a data collection module, a data preprocessing module, a feature extraction module, an identification module, and a data visualization module. The data collection module is used to collect network communication data; the data preprocessing module is used to preprocess and clean the collected communication data; the feature extraction module is used to extract key feature information from the data; the identification module is used to analyze and compare data feature information and identify anomalies in data communication; and the data visualization module is used to visualize and present the abnormal data. The data collection module is connected to the data preprocessing module, the data preprocessing module is connected to the feature extraction module, the feature extraction module is connected to the identification module, and the identification module is connected to the data visualization module.

[0010] As a further description of the above technical solution, the data communication anomaly algorithm model is the GoogleNet-Unet+ model. The backbone network of the GoogleNet-Unet+ model adopts the GoogleNetV2 network, and the task network adopts the Unet network. The GoogleNetV2 network includes 3×3 and 7×7 convolutional layers for feature extraction, an inception module composed of multiple 3×3 and 1×1 convolutional blocks, a BN layer, a max pooling layer, an average pooling layer, and a depth residual module. The Unet network is an encoder-decoder structure. The GoogleNet-Unet model first ports the inception module and the depth residual module from GoogleNetV2 to the encoder of the Unet network. Then, it uses inception modules of different depths according to the position of the Unet encoder to extract features. Finally, the extracted features are sequentially connected to the corresponding positions of the decoder for feature fusion. The depth residual module adopts a DRN network. The DRN network assigns higher weights to the union data information image data through weighted averaging, thereby obtaining a new image sequence with reduced noise interference. The new image sequence is: (1) In equation (1), The input is the union data information image data, w represents the weighting function, t represents the union data information image time series, and b represents the weighted average time interval; Discrete union data is processed in the convolutional layer to complete the feature mapping of the union data image. The feature mapping function is: (2) In equation (2), The feature map representing the output union data information image. Represents the probability density function; The DRN network connects the shallow network to the mapping layer through a connection method. The mapping layer function is: (3) In equation (3), This represents the image feature vector output by the mapping layer. This represents the output vector of the shallow network. This represents the union data information image data input from the previous layer, where t represents the network node number. This represents the feature map bias vector.

[0011] As a further description of the above technical solution, the intelligent routing matching unit adopts BGP and OSPF protocols, the data compression unit adopts a hybrid compression algorithm model based on LZO and Gzip, the hybrid compression algorithm model includes a partitioning module, a mapping module, and a replacement module. The partitioning module divides the input data into small blocks, the mapping module maps frequently occurring characters with short codes and infrequently occurring characters with long codes, and finally the replacement module uses a hash table to replace duplicate strings. The data caching unit uses memcache and redis to cache communication network data, and the data sharding unit uses the Hadoop big data processing platform to shard and process data in parallel.

[0012] As a further description of the above technical solution, the data encryption adopts an improved RSA and AES hybrid encryption algorithm. The improved RSA and AES hybrid encryption algorithm model includes a data encoding module, a data protocol conversion module, an acceleration module, an encryption module, and a decryption module, wherein: The encryption module works by generating a random AES key from the input data. Encrypted using an RSA public key, the following is obtained: (4) In equation (4), For AES key, This is the RSA encryption process, where mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, e is the public key, W is the accelerator, and J is the algorithm efficiency. Here, β represents the key data sequence, and β represents the transformed data sequence. Indicates the encryption protocol; The plaintext M is encrypted using the AES algorithm to obtain... (5) In equation (5), C represents the encryption result. M is the AES key, and M is the plaintext. The decryption module works as follows: the receiver uses the RSA private key to decrypt. The original AES key is obtained, and the decryption function is: (6) In equation (6), For AES key, For the RSA decryption process, mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, and d is the private key; The received ciphertext C is decrypted using the AES algorithm to obtain the plaintext. The decryption algorithm is as follows: (7) In equation (7), M is the original AES key obtained by the receiver, and M is the plaintext that is finally decrypted.

[0013] As a further description of the above technical solution, the main controller includes an FPGA+DSP processing module. The DSP processing module is an ATMega328 acquisition chip, integrating 14 GPIO interfaces, 6 PWM interfaces, a 12-bit ADC interface, a UART serial port, 1 SPI interface, and 1 I2C interface. The FPGA processing module is an ARTIX-7 series XC7A100T-2FGG484I chip. The FPGA processing module uses a hybrid optimization algorithm based on adaptive ant colony optimization and particle swarm optimization to find the optimal communication path. The hybrid optimization algorithm finds the path according to a probability formula, which is: (8) In equation (8), Let k be the probability that the k-th communication data is in path (i,j). Let (i,j) be the pheromone of the path at time t. Let (i,j) be the heuristic factor for the path (i,j) at time t. Let be the set of paths that communication data k is allowed to access next, and s be the elements of the set of allowed paths. , Let k be the iteration factor, and k be a natural number. The communication data releases pheromones along its path, and the pheromone update formula is: (9) In equation (9), To the degree of volatility, Let (i,j) be the pheromone concentration at path (i,j). For the number of consecutive convergences, The maximum pheromone concentration is given by t, where t is time. This is for data margin; The path is optimized by updating pheromones; the optimization algorithm model is as follows: (10) (11) In equations (10)-(11), For its own speed, The best position an individual has ever experienced. The best position experienced by the population is represented by A, B, and C, which are correction coefficients. The position of the previous moment. This is the velocity vector.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: This invention discloses a monitoring system for wireless transmission union data communication access equipment. The system uses a hybrid optimization algorithm to find the optimal communication path through the main controller of the monitoring center. The network communication equipment monitoring system uses an improved hybrid encryption algorithm and a hybrid compression algorithm to accelerate the data communication network transmission speed. The GoogleNet-Unet+ data communication anomaly algorithm model is used to monitor data communication network anomalies. This greatly improves the communication network transmission efficiency, protects the communication network environment security, and significantly enhances the data information processing, communication, interaction, and processing capabilities. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the overall architecture of the present invention; Figure 2 This is a schematic diagram of the data communication anomaly algorithm model structure; Figure 3 This is a flowchart for anomaly analysis. Figure 4 This is a schematic diagram of a communication access equipment monitoring system. Figure 5 This is a flowchart illustrating the steps of anomaly analysis. Detailed Implementation

[0016] The technical solutions in the embodiments described herein will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. It should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concept of the invention.

[0017] like Figures 1-4 The present invention relates to a wireless transmission trade union data communication access device monitoring system, comprising a monitoring center, communication access devices, sensors, network communication devices, and a maintenance management platform; The monitoring center is used to monitor and manage communication access equipment. The monitoring center includes a main controller, a data center, and a management center. The main controller is used to adjust the working status of each device. The management center includes a communication access equipment monitoring system, a network communication equipment monitoring system, and a sensor monitoring system. The communication access equipment monitoring system is used to monitor the operating status of the devices, network connection status, transmission rate, and device load. The network communication equipment monitoring system uses an improved RSA and AES hybrid encryption algorithm to encrypt data and uses the GoogleNet-Unet+ data communication anomaly algorithm model to analyze data communication anomalies. Communication access equipment is used to implement network communication functions; Sensors are used to monitor equipment status and environmental parameters, and transmit the data to the monitoring center for processing and analysis. Network communication equipment is used to realize data transmission and communication connections. The maintenance management platform is used to realize remote management and maintenance of equipment. The maintenance management platform includes a remote maintenance module and an equipment configuration module. The remote maintenance module is used to detect and display the communication process of each communication access device. The remote maintenance module includes an intelligent routing matching unit, a data compression unit, a data caching unit, and a data fragmentation unit. The equipment configuration module is used to remotely modify the operating parameters of each device. The communication access device is connected to the monitoring center, the monitoring center is connected to the sensors, the monitoring center is connected to the network communication device, and the network communication device is connected to the maintenance and management platform.

[0018] In a further embodiment, the working process of the communication access equipment monitoring system is as follows: First, the monitoring system is rationally designed and laid out based on factors such as equipment type, quantity, and distribution. Then, algorithms and models are selected according to the characteristics and data types of the monitored objects. Next, the monitoring data is used for real-time alarm and feedback. Abnormal situations are responded to and handled promptly according to the alarm priority and processing method. Finally, corresponding management and maintenance plans are formulated based on the communication access equipment monitoring system, and professional technical personnel are assigned to maintain and manage it. The working principle of the monitoring center is as follows: the main controller receives data information from communication access devices, sensors and network communication devices and monitors each device according to the status characteristics obtained by the management center. When data anomalies occur, the main controller calls the data communication anomaly algorithm model to analyze the anomaly in detail and adjust each device effectively according to the corresponding anomaly status to prevent the spread of abnormal data.

[0019] In a further embodiment, the working process of the network communication equipment monitoring system is as follows: First, the network range, data types and requirements, transmission latency, and reliability are analyzed according to the application scenario. Then, the network scale, transmission distance, and node density are comprehensively monitored according to the star, ring, tree, or mesh structure used. Next, wireless technologies and protocols are detected and analyzed according to the application scenario and network topology. Finally, the network communication equipment monitoring system is protected through data encryption and anomaly analysis. The working principle of the network communication equipment monitoring system is as follows: based on the application scenario of the network communication equipment, the network topology and wireless technology and protocols adopted provide security design for the communication network, and formulate corresponding technical solutions and technical personnel support for the management and maintenance of the network communication equipment. By comprehensively monitoring the workflow and working details of the network communication equipment, the system ensures the security of data transmission.

[0020] In a further embodiment, the anomaly analysis method is as follows: Step 1: Detect network anomalies through statistical analysis, machine learning, and data mining; Step 2: Deeply mine and analyze abnormal data through data processing and data visualization; Step 3: Determine the specific location and cause of the anomaly through network topology analysis, route tracing, and port monitoring; Step 4: Repair the anomaly by using software repair, hardware replacement, and network topology adjustment, depending on the specific cause and location of the anomaly. Step 5: Real-time monitoring and management of network operation status through network topology monitoring, device status monitoring, and data traffic monitoring. The implementation process of the anomaly analysis method is as follows: During anomaly detection, appropriate detection algorithms and models need to be selected based on network characteristics and anomaly types to achieve accurate detection and judgment of anomalies. Through data analysis, in-depth mining and analysis of anomaly data can be achieved to identify the characteristics and patterns of the anomaly data. Through fault diagnosis, the specific location and cause of the anomaly can be determined, providing a basis for subsequent repair. When formulating a repair plan, appropriate repair plans need to be selected based on the specific cause and location of the anomaly, and corresponding repair procedures need to be formulated. Through system monitoring, comprehensive monitoring and management of the network can be achieved, anomalies can be detected and resolved in a timely manner, and the stability and reliability of the network can be improved.

[0021] In a further embodiment, the data communication anomaly algorithm model includes a data collection module, a data preprocessing module, a feature extraction module, an identification module, and a data visualization module. The data collection module collects network communication data; the data preprocessing module preprocesses and cleans the collected communication data; the feature extraction module extracts key feature information from the data; the identification module analyzes and compares data feature information and identifies anomalies in data communication; and the data visualization module visualizes the abnormal data. The data collection module is connected to the data preprocessing module, the data preprocessing module is connected to the feature extraction module, the feature extraction module is connected to the identification module, and the identification module is connected to the data visualization module. The data communication anomaly algorithm model works as follows: Data is preprocessed and cleaned to remove useless data and improve data quality. Key features are extracted from the data, including the mean, variance, slope, and kurtosis. The extracted features are input into the anomaly detection module. Through analysis and comparison of these features, anomalies in data communication are identified. The abnormal data is then presented visually to facilitate data analysis and decision-making for users.

[0022] In a further embodiment, the intelligent routing matching unit adopts BGP and OSPF protocols, the data compression unit adopts a hybrid compression algorithm model based on LZO and gzip, the hybrid compression algorithm model includes a partitioning module, a mapping module, and a replacement module. The partitioning module divides the input data into small blocks, the mapping module maps frequently occurring characters with short codes and infrequently occurring characters with long codes, and finally the replacement module uses a hash table to replace duplicate strings. The data caching unit uses memcache and redis to cache communication network data, and the data sharding unit uses the Hadoop big data processing platform to shard and process data in parallel.

[0023] In a further embodiment, the data encryption employs a modified RSA and AES hybrid encryption algorithm. This modified RSA and AES hybrid encryption algorithm model includes a data encoding module, a data protocol conversion module, an acceleration module, an encryption module, and a decryption module, wherein: The encryption module works by generating a random AES key from the input data. Encrypted using an RSA public key, the following is obtained: (4) In equation (4), For AES key, This is the RSA encryption process, where mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, e is the public key, W is the accelerator, and J is the algorithm efficiency. Here, β represents the key data sequence, and β represents the transformed data sequence. Indicates the encryption protocol; The plaintext M is encrypted using the AES algorithm to obtain... (5) In equation (5), C represents the encryption result. M is the AES key, and M is the plaintext. The decryption module works as follows: the receiver uses the RSA private key to decrypt. The original AES key is obtained, and the decryption function is: (6) In equation (6), For AES key, For the RSA decryption process, mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, and d is the private key; The received ciphertext C is decrypted using the AES algorithm to obtain the plaintext. The decryption algorithm is as follows: (7) In equation (7), M is the original AES key obtained by the receiver, and M is the plaintext that is finally decrypted. The improved hybrid encryption algorithm model works as follows: The client starts and sends a request to the server. The server generates a public key 1 and a private key 1 using the RSA algorithm and returns public key 1 to the client. After receiving public key 1 from the server, the client generates a public key 2 and a private key 2 using the RSA algorithm and encrypts public key 2 using public key 1 from the server. The encrypted data is then transmitted to the server. The server receives the ciphertext from the client and decrypts it using private key 1. Since data 2 is encrypted using the server's public key 2, decryption yields the client-generated public key 2. The server then generates its own symmetric key, named aeskey (AES), and encrypts it using the client's public key 2 before returning it to the client. Because data encrypted with public key 2 can only be decrypted by the client's corresponding private key 2, the client decrypts the ciphertext using private key 2. After decryption, the client obtains the AES symmetric encryption key. Finally, the key is used for data encryption. The entire process ends here, and the encryption and decryption are shown in Table 1.

[0024] Table 1 Encryption and Decryption Process Table enter encryption private key Decryption 123478 ACBGDX 1W36 123478 1789085 ANGRYOP 123C 1789085 67890858 WNMKSTRF P78K 67890858 As shown in Table 1, different lengths of inputs will produce corresponding lengths of encrypted results. The length of the private key is the same. After two encryption and decryption processes, the result will eventually return to the input, and the receiver will receive the important ciphertext.

[0025] In a further embodiment, the main controller includes an FPGA+DSP processing module. The DSP processing module is an ATMega328 acquisition chip, integrating 14 GPIO interfaces, 6 PWM interfaces, a 12-bit ADC interface, a UART serial port, 1 SPI interface, and 1 I2C interface. The FPGA processing module is an ARTIX-7 series XC7A100T-2FGG484I chip. The FPGA processing module uses a hybrid optimization algorithm based on adaptive ant colony optimization and particle swarm optimization to find the optimal communication path. The hybrid optimization algorithm finds the path according to a probability formula, which is: (8) In equation (8), Let k be the probability that the k-th communication data is in path (i,j). Let (i,j) be the pheromone of the path at time t. Let (i,j) be the heuristic factor for the path (i,j) at time t. Let be the set of paths that communication data k is allowed to access next, and s be the elements of the set of allowed paths. , Let k be the iteration factor, and k be a natural number. The communication data releases pheromones along its path, and the pheromone update formula is: (9) In equation (9), To the degree of volatility, Let (i,j) be the pheromone concentration at path (i,j). For the number of consecutive convergences, The maximum pheromone concentration is given by t, where t is time. This is for data margin; The path is optimized by updating pheromones; the optimization algorithm model is as follows: (10) (11) In equations (10)-(11), For its own speed, The best position an individual has ever experienced. The best position experienced by the population is represented by A, B, and C, which are correction coefficients. The position of the previous moment. It is a velocity vector. The principle of the hybrid optimization algorithm is as follows: In the process of constructing a solution, the hybrid optimization algorithm uses a strategy that combines deterministic selection and random selection. During the search process, the probability of deterministic selection is dynamically adjusted, the random positions and velocities of individuals in the population are initialized, and solutions with better reinforcement performance are obtained based on the principle of positive feedback. Then, the fitness of individuals in the population is evaluated, the historical best position is found, the group's best position is found, and finally, the position and velocity are updated. When the evolution reaches a certain number of generations, the evolutionary direction is basically determined. At this time, the information on the path is dynamically adjusted. The hybrid optimization algorithm can accelerate the convergence speed of the algorithm and escape local optima, as shown in Table 2.

[0026] Table 2 Path Optimization Table node A B C D E F Results / s Adaptive Ant Colony Algorithm 1 4 2 6 3 5 50 Particle Swarm Optimization Algorithm 2 3 1 4 6 5 30 Hybrid optimization algorithm 3 1 6 4 5 2 10 As shown in Table 2, by comparing the time consumed by the three algorithms in finding the optimal path, the hybrid optimization algorithm takes the shortest time and plans the optimal communication path, thus greatly accelerating the detailed planning of the optimal communication path.

[0027] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these specific embodiments are merely illustrative. Those skilled in the art can omit, substitute, and modify the details of the above methods and systems in various ways without departing from the principles and essence of the present invention. For example, combining the above method steps to perform substantially the same function and achieve substantially the same result according to substantially the same method falls within the scope of the present invention. Therefore, the scope of the present invention is defined only by the appended claims.

Claims

1. A wireless transmission-based trade union data communication access device monitoring system, characterized in that: This includes a monitoring center, communication access equipment, sensors, network communication equipment, and a maintenance and management platform. The monitoring center is used to monitor and manage communication access equipment. The monitoring center includes a main controller, a data center, and a management center. The main controller is used to adjust the working status of each device. The management center includes a communication access equipment monitoring system, a network communication equipment monitoring system, and a sensor monitoring system. The communication access equipment monitoring system is used to monitor the operating status of the devices, network connection status, transmission rate, and device load. The network communication equipment monitoring system uses an improved RSA and AES hybrid encryption algorithm to encrypt data and uses the GoogleNet-Unet+ data communication anomaly algorithm model to analyze data communication anomalies. Communication access equipment is used to implement network communication functions; Sensors are used to monitor equipment status and environmental parameters, and transmit the data to the monitoring center for processing and analysis. Network communication equipment is used to realize data transmission and communication connections. The maintenance management platform is used to realize remote management and maintenance of equipment. The maintenance management platform includes a remote maintenance module and an equipment configuration module. The remote maintenance module is used to detect and display the communication process of each communication access device. The remote maintenance module includes an intelligent routing matching unit, a data compression unit, a data caching unit, and a data fragmentation unit. The equipment configuration module is used to remotely modify the operating parameters of each device. The communication access device is connected to the monitoring center, the monitoring center is connected to the sensors, the monitoring center is connected to the network communication device, and the network communication device is connected to the maintenance and management platform.

2. The wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The working process of the communication access equipment monitoring system is as follows: First, the monitoring system is reasonably designed and laid out according to the factors of equipment type, quantity and distribution. Then, the algorithm and model are selected according to the characteristics and data type of the monitored object. Next, the monitoring data is alarmed and fed back in real time. Abnormal situations are responded to and handled in a timely manner according to the priority and processing method of the alarm. Finally, corresponding management and maintenance plans are formulated according to the communication access equipment monitoring system and professional technical personnel are assigned to maintain and manage it.

3. The wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The working process of the network communication equipment monitoring system is as follows: First, the network range, data type and requirements, transmission latency and reliability are analyzed according to the application scenario. Then, the network scale, transmission distance and node density are comprehensively monitored according to the star, ring, tree or mesh structure adopted. Next, the wireless technology and protocol are detected and analyzed according to the application scenario and network topology. Finally, the network communication equipment monitoring system is protected by data encryption and anomaly analysis.

4. The wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The anomaly analysis method is as follows: Step 1: Detect network anomalies through statistical analysis, machine learning, and data mining; Step 2: Deeply mine and analyze abnormal data through data processing and data visualization; Step 3: Determine the specific location and cause of the anomaly through network topology analysis, route tracing, and port monitoring; Step 4: Repair the anomaly by using software repair, hardware replacement, and network topology adjustment, depending on the specific cause and location of the anomaly. Step 5: Real-time monitoring and management of network operation status through network topology monitoring, device status monitoring, and data traffic monitoring.

5. A wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The data communication anomaly algorithm model includes a data collection module, a data preprocessing module, a feature extraction module, an identification module, and a data visualization module. The data collection module is used to collect network communication data. The data preprocessing module is used to preprocess and clean the collected communication data. The feature extraction module is used to extract key feature information from the data. The identification module is used to analyze and compare data feature information and identify anomalies in data communication. The data visualization module is used to visualize and present the abnormal data. The data collection module is connected to the data preprocessing module, the data preprocessing module is connected to the feature extraction module, the feature extraction module is connected to the identification module, and the identification module is connected to the data visualization module.

6. A wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The data communication anomaly algorithm model is the GoogleNet-Unet+ model. The backbone network of the GoogleNet-Unet+ model uses the GoogleNetV2 network, and the task network uses the Unet network. The GoogleNetV2 network includes 3×3 and 7×7 convolutional layers for feature extraction, an inception module composed of multiple 3×3 and 1×1 convolutional blocks, a batch normalization (BN) layer, a max pooling layer, an average pooling layer, and a depth residual module. The Unet network is an encoder-decoder structure. The GoogleNet-Unet model first ports the inception and depth residual modules from GoogleNetV2 to the encoder of the Unet network. Then, it uses inception modules of different depths according to the position of the Unet encoder to extract features. Finally, the extracted features are sequentially connected to the corresponding positions in the decoder for feature fusion. The depth residual module uses a DRN network. The DRN network assigns higher weights to the union data information image data through weighted averaging, thereby obtaining a new image sequence with reduced noise interference. The new image sequence is: (1) In equation (1), The input is the union data information image data, w represents the weighting function, t represents the union data information image time series, and b represents the weighted average time interval; Discrete union data is processed in the convolutional layer to complete the feature mapping of the union data image. The feature mapping function is: （2） In equation (2), The feature map representing the output union data information image. Represents the probability density function; The DRN network connects the shallow network to the mapping layer through a connection method. The mapping layer function is: （3） In equation (3), This represents the image feature vector output by the mapping layer. This represents the output vector of the shallow network. This represents the union data information image data input from the previous layer, where t represents the network node number. This represents the feature map bias vector.

7. A wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The intelligent routing matching unit uses BGP and OSPF protocols, and the data compression unit uses a hybrid compression algorithm model based on LZO and Gzip. The hybrid compression algorithm model includes a partitioning module, a mapping module, and a replacement module. The partitioning module divides the input data into small blocks. The mapping module maps frequently occurring characters with short codes and infrequently occurring characters with long codes. Finally, the replacement module uses a hash table to replace duplicate strings. The data caching unit uses memcache and redis to cache communication network data, and the data sharding unit uses the Hadoop big data processing platform to shard and process data in parallel.

8. A wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The data encryption employs a modified RSA and AES hybrid encryption algorithm. This modified RSA and AES hybrid encryption algorithm model includes a data encoding module, a data protocol conversion module, an acceleration module, an encryption module, and a decryption module, wherein: The encryption module works by generating a random AES key from the input data. Encrypted using an RSA public key, the following is obtained: (4) In equation (4), For AES key, This is the RSA encryption process, where mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, e is the public key, W is the accelerator, and J is the algorithm efficiency. Here, β represents the key data sequence, and β represents the transformed data sequence. Indicates the encryption protocol; The plaintext M is encrypted using the AES algorithm to obtain... (5) In equation (5), C represents the encryption result. M is the AES key, and M is the plaintext. The decryption module works as follows: the receiver uses the RSA private key to decrypt. The original AES key is obtained, and the decryption function is: (6) In equation (6), For AES key, For the RSA decryption process, mod is the modulo operation, n is the product of prime numbers, p and q are very large prime numbers, and d is the private key; The received ciphertext C is decrypted using the AES algorithm to obtain the plaintext. The decryption algorithm is as follows: (7) In equation (7), M is the original AES key obtained by the receiver, and M is the plaintext that is finally decrypted.

9. A wireless transmission trade union data communication access device monitoring system according to claim 1, characterized in that: The main controller includes an FPGA+DSP processing module. The DSP processing module is an ATMega328 data acquisition chip, integrating 14 GPIO interfaces, 6 PWM interfaces, a 12-bit ADC interface, a UART serial port, 1 SPI interface, and 1 I2C interface. The FPGA processing module is an ARTIX-7 series XC7A100T-2FGG484I chip. The FPGA processing module uses a hybrid optimization algorithm based on adaptive ant colony optimization and particle swarm optimization to find the optimal communication path. The hybrid optimization algorithm finds the path according to a probability formula, which is: （8） In equation (8), Let k be the probability that the k-th communication data is in path (i,j). Let (i,j) be the pheromone of the path at time t. Let (i,j) be the heuristic factor for the path (i,j) at time t. Let be the set of paths that communication data k is allowed to access next, and s be the elements of the set of allowed paths. , Let k be the iteration factor, and k be a natural number. The communication data releases pheromones along its path, and the pheromone update formula is: （9） In equation (9), To the degree of volatility, Let (i,j) be the pheromone concentration at path (i,j). For the number of consecutive convergences, The maximum pheromone concentration is given by t, where t is time. This is for data margin; The path is optimized by updating pheromones; the optimization algorithm model is as follows: (10) （11） In equations (10)-(11), For its own speed, The best position an individual has ever experienced. The best position experienced by the population is represented by A, B, and C, which are correction coefficients. The position of the previous moment. This is the velocity vector.

Images