Electromechanical equipment wireless internet-of-things control system and method based on multi-protocol adaptive conversion

Abstract

The invention discloses an electromechanical equipment wireless Internet of Things control system and method based on multi-protocol adaptive conversion, and relates to the technical field of Internet of Things. Universal features, protocol features and interference evaluation indexes related to interference are extracted, a LightGBM model with the universal features and the protocol features as input and an interference evaluation index weighted value as output is constructed, and a neural network prediction model with important features as input and the interference evaluation indexes as output is constructed. An interference adjustment strategy and a corresponding adjustment rule are defined, an optimal interference adjustment strategy used for adjusting parameters of the wireless communication system is selected according to a judgment result of whether an interference prediction result triggers the adjustment rule, and a deep learning model is utilized to analyze and predict a complex dynamic industrial environment. Optimized communication parameters are optimized in real time, so that the adaptive capacity of anti-interference measures in a dynamic environment is improved, and the high-stability production requirement for communication in industrial production is met.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a wireless Internet of Things control system and method for electromechanical equipment based on multi-protocol adaptive conversion. Background Art

[0002] With the rapid development of industrial automation and the Internet of Things (IoT) technologies, the demand for interconnectivity among electromechanical devices is increasing. Modern industrial environments feature a wide variety of electromechanical devices, each using a variety of communication protocols, such as Modbus, Profibus, HART, and DLT645. These protocols differ significantly in data format, transmission rate, and communication methods, making direct communication between devices challenging. Furthermore, with the widespread adoption of wireless communication technology, an increasing number of electromechanical devices are adopting wireless communication for remote monitoring and control. However, the complex wireless communication environment, coupled with issues such as signal interference and transmission distance limitations, pose new challenges to stable device communication.

[0003] In complex industrial environments, multiple wireless signals, such as Wi-Fi, Bluetooth, ZigBee, and 4G / 5G, coexist, causing significant mutual interference. Furthermore, electromagnetic interference, equipment obstruction, and signal attenuation in industrial scenarios can also impact the stability of wireless communications. While existing technologies can employ anti-interference measures such as frequency hopping and spread spectrum, industrial environments are complex and dynamic. These anti-interference measures lack adaptability in dynamic environments, making it difficult to optimize communication parameters in real time to address sudden interference, and thus fail to meet the production requirements for highly stable communications. Therefore, a wireless IoT control system and method for electromechanical equipment based on multi-protocol adaptive conversion is proposed. Summary of the Invention

[0004] The main purpose of the present invention is to provide a wireless Internet of Things control system and method for electromechanical equipment based on multi-protocol adaptive conversion, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for controlling wireless Internet of Things (IoT) of electromechanical equipment based on multi-protocol adaptive conversion includes:

[0007] Step 1: Automatically identify the communication protocol used by the electromechanical device by analyzing the format, header information and characteristic fields of the data packet, develop a parser for each communication protocol, and parse the data of different communication protocols into a unified intermediate format through the parser;

[0008] Step 2: Collect electromagnetic signal data in the wireless communication environment, including signal strength, frequency, bandwidth, interference type, and channel quality, and clean, denoise, and normalize the collected raw data to remove invalid or abnormal data;

[0009] Step 3: Extract common features and protocol features related to interference, as well as interference evaluation index data from the preprocessed data, and construct a LightGBM model with common features and protocol features as input and interference evaluation index weighted values ​​as output. Use the training set data to train the LightGBM model, and adjust the basic parameters of LightGBM until its performance index reaches the first expected value. Use the trained LightGBM model to output the importance score of each feature, and screen out features within the set importance score threshold range as important features.

[0010] Step 4: Constructing a neural network prediction model with the important features as input and the interference evaluation index as output, using the collected historical data to train the neural network prediction model until its prediction accuracy reaches a second expected value, and using the trained neural network prediction model to input the prediction result of the interference evaluation index at the next moment;

[0011] Step 5: define an interference adjustment strategy and corresponding adjustment rules, and select an optimal interference adjustment strategy for adjusting wireless communication system parameters based on a determination result of whether the interference prediction result triggers the adjustment rules.

[0012] A wireless Internet of Things control system for electromechanical equipment based on multi-protocol adaptive conversion adopts a layered architecture and includes:

[0013] The device layer includes various electromechanical devices that support Modbus, Profibus, DLT645, ZigBee, and Wi-Fi communication protocols;

[0014] The protocol conversion layer is responsible for identifying and converting the communication protocols of different devices and realizing adaptive conversion of protocols.

[0015] The perception layer is used to collect electromagnetic signal data in the wireless communication environment, including signal strength, frequency, bandwidth, interference type and channel quality;

[0016] The data processing layer is used to preprocess, extract features and perform preliminary analysis on the collected data.

[0017] Intelligent analysis layer: used to analyze data, predict interference and optimize communication parameters;

[0018] Application layer: provides user interface and control functions to realize remote monitoring and management of equipment;

[0019] Wherein, the protocol conversion layer includes

[0020] The communication protocol identification submodule is used to automatically identify the communication protocol used by the electromechanical device by analyzing the format, header information and characteristic fields of the data packet;

[0021] A parser module, wherein the parser module integrates several parsers for different communication protocols, and parses the data of different communication protocols into a unified intermediate format through the parsers;

[0022] The perception layer includes:

[0023] The data acquisition submodule is used to collect electromagnetic signal data including signal strength, frequency, bandwidth, interference type and channel quality in the wireless communication environment;

[0024] The data processing layer includes:

[0025] The data processing submodule is used to clean, denoise, and normalize the collected raw data to remove invalid or abnormal data;

[0026] Feature extraction submodule, used to extract general features and protocol features related to interference, as well as interference evaluation indicators from the preprocessed data;

[0027] The LightGBM model construction submodule is used to build a LightGBM model with general features and protocol features as input and the weighted value of interference evaluation index as output;

[0028] The LightGBM model training submodule is used to train the LightGBM model using the training set data and adjust the basic parameters of LightGBM until its performance index reaches the first expected value;

[0029] The feature importance score output submodule is used to output the importance score of each feature using the trained LightGBM model;

[0030] The feature screening submodule is used to screen out features within a set importance score threshold as important features;

[0031] The intelligent analysis layer includes:

[0032] A neural network prediction model construction submodule is used to construct a neural network prediction model with the important features as input and the interference evaluation index as output;

[0033] A neural network prediction model training submodule is used to train the neural network prediction model using the collected historical data until its prediction accuracy reaches a second expected value;

[0034] The prediction result output submodule is used to input the prediction result of the interference evaluation index at the next moment using the trained neural network prediction model;

[0035] The adjustment strategy definition submodule is used to define the interference adjustment strategy and the corresponding adjustment rules;

[0036] An adjustment strategy selection submodule, configured to select an optimal interference adjustment strategy for adjusting wireless communication system parameters based on a determination result of whether the interference prediction result triggers the adjustment rule;

[0037] The application layer includes:

[0038] The device control submodule is used to provide a user interface and control functions to achieve remote monitoring and management of the device.

[0039] The control system further includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0040] Furthermore, the common features include:

[0041] Signal strength for evaluating signal quality;

[0042] The signal-to-noise ratio is used to reflect the clarity of the signal in a noisy environment;

[0043] Interference intensity used to assess the extent to which noise affects the signal;

[0044] Spectrum occupancy rate, which reflects the usage of spectrum resources;

[0045] Bit error rate used to reflect communication quality;

[0046] Channel utilization, which reflects the busyness of the channel;

[0047] The packet loss rate reflects the proportion of data packets lost during transmission;

[0048] The modulation and demodulation method used;

[0049] Transmission distance used to reflect the physical distance between devices;

[0050] and a timestamp.

[0051] Furthermore, the protocol features include Modbus protocol features, Profibus protocol features, DLT645 protocol features and ZigBee protocol features; wherein,

[0052] The Modbus protocol features include:

[0053] A register address for identifying the location where data is stored;

[0054] Function code for specifying the type of operation;

[0055] The Modbus protocol data frame format is as follows: the structure of the Modbus data frame includes a start bit, an address field, a function code field, a data field, and a check bit;

[0056] The Profibus protocol features include:

[0057] A frame type used to indicate the type of the data frame;

[0058] Device address used to identify the device address in the Profibus network;

[0059] Transport protocols;

[0060] The DLT645 protocol features include:

[0061] A meter address used to identify the address of an electric meter or other device;

[0062] The DLT645 protocol data frame format is as follows: The structure of the DLT645 data frame includes a frame header, an address field, a control code, a data field, and a check bit;

[0063] Code control code used to specify the type of operation;

[0064] The ZigBee protocol features include:

[0065] The network address used to identify the device address in the ZigBee network;

[0066] PAN ID, a unique identifier used to identify the ZigBee network;

[0067] Transfer rate.

[0068] Furthermore, the interference evaluation index includes:

[0069] Interference intensity is used to evaluate the impact of interference signals on useful signals;

[0070] Interference probability, which reflects the probability of interference occurring within a specific time period;

[0071] Interference type used to reflect how unwanted signals affect wanted signals;

[0072] The calculation method of the weighted value of interference evaluation index is: In the formula, Ie -weighting is the weighted value of interference evaluation index; Ie j is the j-th interference evaluation index value; is the weight of the j-th interference evaluation index, and

[0073] Furthermore, the interference adjustment strategy includes:

[0074] a first adjustment strategy for adjusting the communication channel;

[0075] The adjustment rules of the first adjustment strategy include:

[0076] When the predicted interference evaluation index weighted value is higher than the set first threshold, switching to the communication channel with the smallest predicted interference evaluation index weighted value;

[0077] a second adjustment strategy for adjusting transmit power;

[0078] The adjustment rules of the second adjustment strategy include:

[0079] When the predicted interference evaluation index weighted value is higher than the set second threshold, the transmit power is increased to enhance the signal strength;

[0080] When the predicted interference evaluation index weighted value is lower than the set third threshold, the transmit power is reduced to save energy and reduce interference to other devices;

[0081] A third adjustment strategy for adjusting the modulation mode;

[0082] The adjustment rules of the third adjustment strategy include:

[0083] When the predicted interference evaluation index weighted value is higher than the set fourth threshold, switch to a modulation mode with stronger anti-interference capability;

[0084] When the predicted interference evaluation index weighted value is lower than the set fifth threshold, switch to a higher-order modulation mode to increase the data transmission rate;

[0085] A fourth adjustment strategy for adjusting the size of data packets;

[0086] The adjustment rules of the fourth adjustment strategy include:

[0087] When the predicted interference evaluation index weighted value is higher than the set sixth threshold, the data packet size is reduced to reduce transmission errors and retransmission probability;

[0088] When the predicted interference evaluation index weighted value is lower than the set seventh threshold, the data packet size is increased to improve transmission efficiency;

[0089] A fifth adjustment strategy for adjusting the transmission rate;

[0090] The adjustment rules of the fifth adjustment strategy include:

[0091] When the predicted interference evaluation index weighted value is higher than the set eighth threshold, the transmission rate is reduced to reduce the bit error rate;

[0092] When the predicted interference evaluation index weighted value is lower than the set 9th threshold, the transmission rate is increased to improve the system throughput;

[0093] A sixth adjustment strategy for adjusting multiple antennas;

[0094] The adjustment rules of the sixth adjustment strategy include:

[0095] When the predicted interference evaluation index weighted value is higher than the set 10th threshold, beamforming technology is enabled to focus the signal in the target direction to reduce interference;

[0096] When the predicted interference evaluation index weighted value is lower than the set 11th threshold, the MIMO technology is enabled to increase the data transmission rate.

[0097] Furthermore, the neural network prediction model is a BP neural network prediction model with a three-layer structure including an input layer, an output layer and an output layer, wherein the number of neurons in the input layer is equal to the number of input features; the number of neurons in the output layer is equal to the number of types of output interference evaluation indicators.

[0098] The present invention has the following beneficial effects:

[0099] Compared with the existing technology, by automatically identifying the communication protocol used by electromechanical equipment, parsing the data of different communication protocols into a unified intermediate format, collecting electromagnetic signal data in the wireless communication environment for processing, extracting general features and protocol features related to interference, and interference evaluation index data, a LightGBM model is constructed with general features and protocol features as input and interference evaluation index weighted values ​​as output. The trained LightGBM model is used to output the importance score of each feature, and features within the set importance score threshold range are screened out as important features. A neural network prediction model is constructed with the important features as input and the interference evaluation index as output. The trained neural network prediction model is used to input the predicted results of the interference evaluation index at the next moment, and the interference adjustment strategy and the corresponding adjustment rules are defined. According to the judgment result of whether the interference prediction result triggers the adjustment rule, the optimal interference adjustment strategy for adjusting the parameters of the wireless communication system is selected. The deep learning model can be used to analyze and predict the complex dynamic industrial environment, and optimize the communication parameters in real time to improve the adaptability of anti-interference measures in dynamic environments, thereby meeting the high stability production requirements for communication in industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] Figure 1Schematic diagram of the flow of the method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion of the present invention;

[0101] Figure 2 This is a schematic structural diagram of a wireless Internet of Things control system for electromechanical equipment based on multi-protocol adaptive conversion according to the present invention;

[0102] Figure 3 This is a structural diagram of the neural network prediction model constructed in this scheme. DETAILED DESCRIPTION

[0103] The present invention will be further described below in conjunction with specific embodiments. The accompanying drawings are for illustrative purposes only and represent only schematic diagrams rather than actual drawings. They should not be understood as limiting the present invention. In order to better illustrate the specific embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0104] Example 1

[0105] The specific implementation process of the technical solution of the present invention includes the following steps:

[0106] Step 1: Obtain communication data packets between electromechanical devices, automatically identify the communication protocols used by the electromechanical devices by analyzing the format, header information and characteristic fields of the data packets, develop parsers for each communication protocol, and use the parsers to parse data of different communication protocols into a unified intermediate format; among them, the communication protocols include Modbus protocol, Profibus protocol, DLT645 protocol and ZigBee protocol.

[0107] Step 2: Collect electromagnetic signal data in the wireless communication environment, including signal strength, frequency, bandwidth, interference type, and channel quality, and clean, denoise, and normalize the collected raw data to remove invalid or abnormal data.

[0108] Step 3: extracting interference-related general features and protocol features, as well as interference evaluation index data from the preprocessed data;

[0109] Among them, common features include:

[0110] Signal strength for evaluating signal quality;

[0111] The signal-to-noise ratio is used to reflect the clarity of the signal in a noisy environment;

[0112] Interference intensity used to assess the extent to which noise affects the signal;

[0113] Spectrum occupancy rate, which reflects the usage of spectrum resources;

[0114] Bit error rate used to reflect communication quality;

[0115] Channel utilization, which reflects the busyness of the channel;

[0116] The packet loss rate reflects the proportion of data packets lost during transmission;

[0117] The modulation and demodulation method used;

[0118] Transmission distance used to reflect the physical distance between devices;

[0119] and timestamp;

[0120] The protocol features include Modbus protocol features, Profibus protocol features, DLT645 protocol features and ZigBee protocol features; among them,

[0121] Modbus protocol features include:

[0122] Register address used to identify the data storage location. Different register addresses may correspond to different device states or data types.

[0123] Function code used to specify the operation type. Common function codes include 01 (read coil status) and 03 (read holding register).

[0124] The Modbus protocol data frame format is as follows: the structure of the Modbus data frame includes a start bit, an address field, a function code field, a data field, and a check bit;

[0125] Profibus protocol features include:

[0126] Frame type used to indicate the type of data frame, such as request frame, response frame, etc. Different frame types may correspond to different communication behaviors;

[0127] Device address used to identify the device address in the Profibus network. Different device addresses correspond to different devices or device groups.

[0128] Transmission protocol: Profibus supports multiple transmission protocols, such as DP (distributed peripherals) and PA (process automation). Different protocols may have different data transmission rules and characteristics.

[0129] DLT645 protocol features include:

[0130] A meter address used to identify the address of an electric meter or other device, where different meter addresses correspond to different devices or device groups;

[0131] The DLT645 protocol data frame format is as follows: The structure of the DLT645 data frame includes a frame header, an address field, a control code, a data field, and a check bit;

[0132] Code control code used to specify the operation type. Different control codes correspond to different operation behaviors.

[0133] ZigBee protocol features include:

[0134] The network address used to identify the device address in the ZigBee network. Different network addresses correspond to different devices or device groups.

[0135] PAN ID, a unique identifier used to identify the ZigBee network. Different PAN IDs correspond to different ZigBee networks.

[0136] Transmission rate: ZigBee supports multiple transmission rates, such as 250kbps and 1Mbps. Different transmission rates may affect the stability and efficiency of communication.

[0137] The role of features

[0138] Common features: These are used to assess the overall quality of the wireless communication environment and are applicable to devices of all protocols. They are the basis for interference prediction and communication optimization.

[0139] Protocol-specific features: Used to understand the behavior and characteristics of specific protocols, which helps optimize protocol conversion and device management and provide more fine-grained control and optimization.

[0140] Interference evaluation indicators include:

[0141] Interference intensity is used to evaluate the impact of interference signals on useful signals;

[0142] Interference probability, which reflects the probability of interference occurring within a specific time period;

[0143] Interference type used to reflect how unwanted signals affect wanted signals.

[0144] Step 4: Build a LightGBM model with common features and protocol features as input and interference evaluation index weighted value as output. Use the training set data to train the LightGBM model, and adjust the basic parameters of LightGBM until its performance index reaches the first expected value. Use the trained LightGBM model to output the importance score of each feature, and screen out features within the set importance score threshold range as important features.

[0145] The calculation method of the weighted value of interference evaluation index is: In the formula, Ie -weightingis the weighted value of interference evaluation index; Ie j is the j-th interference evaluation index value; is the weight of the j-th interference evaluation index, and

[0146] Step 5: Construct a neural network prediction model with important features as input and interference evaluation index as output. Use the collected historical data to train the neural network prediction model until its prediction accuracy reaches a second expected value. Then, use the trained neural network prediction model to input the prediction result of the interference evaluation index at the next moment.

[0147] The neural network prediction model is a BP neural network prediction model with a three-layer structure consisting of an input layer, an output layer and an output layer. Figure 3 As shown in the structural diagram, the number of neurons in the input layer is equal to the number of input features; the number of neurons in the output layer is equal to the number of types of output interference evaluation indicators.

[0148] Step 6: define an interference adjustment strategy and corresponding adjustment rules, and select an optimal interference adjustment strategy for adjusting wireless communication system parameters based on a determination result of whether the interference prediction result triggers the adjustment rule.

[0149] Interference adjustment strategies include:

[0150] a first adjustment strategy for adjusting the communication channel;

[0151] Adjustment goal: Select a channel with less interference to optimize communication performance;

[0152] Application scenarios: Applicable to multi-channel wireless communication systems such as Wi-Fi and ZigBee;

[0153] The adjustment rules of the first adjustment strategy include:

[0154] When the predicted interference evaluation index weighted value is higher than the set first threshold, switching to the communication channel with the smallest predicted interference evaluation index weighted value;

[0155] a second adjustment strategy for adjusting transmit power;

[0156] Adjustment target: Reduce interference or enhance signal strength by adjusting transmit power;

[0157] Application scenarios: Applicable to all wireless communication systems, especially those requiring energy saving;

[0158] The adjustment rules of the second adjustment strategy include:

[0159] When the predicted interference evaluation index weighted value is higher than the set second threshold, the transmit power is increased to enhance the signal strength;

[0160] When the predicted interference evaluation index weighted value is lower than the set third threshold, the transmit power is reduced to save energy and reduce interference to other devices;

[0161] A third adjustment strategy for adjusting the modulation mode;

[0162] Adjustment goal: Select a modulation method that is more suitable for the current interference environment;

[0163] Application scenarios: Suitable for scenarios where the transmission rate needs to be optimized in different interference environments;

[0164] The adjustment rules of the third adjustment strategy include:

[0165] When the predicted interference evaluation index weighted value is higher than the set fourth threshold, switch to a modulation mode with stronger anti-interference capability;

[0166] When the predicted interference evaluation index weighted value is lower than the set fifth threshold, switch to a higher-order modulation mode to increase the data transmission rate;

[0167] A fourth adjustment strategy for adjusting the size of data packets;

[0168] Adjustment goal: Optimize transmission efficiency by adjusting the packet size;

[0169] Application scenarios: Applicable to scenarios that require dynamic optimization of data transmission efficiency;

[0170] The adjustment rules of the fourth adjustment strategy include:

[0171] When the predicted interference evaluation index weighted value is higher than the set sixth threshold, the data packet size is reduced to reduce transmission errors and retransmission probability;

[0172] When the predicted interference evaluation index weighted value is lower than the set seventh threshold, the data packet size is increased to improve transmission efficiency;

[0173] A fifth adjustment strategy for adjusting the transmission rate;

[0174] Adjustment target: Dynamically adjust the transmission rate according to the interference situation;

[0175] Application scenarios: Applicable to scenarios that require dynamic optimization of transmission rate;

[0176] The adjustment rules of the fifth adjustment strategy include:

[0177] When the predicted interference evaluation index weighted value is higher than the set eighth threshold, the transmission rate is reduced to reduce the bit error rate;

[0178] When the predicted interference evaluation index weighted value is lower than the set 9th threshold, the transmission rate is increased to improve the system throughput;

[0179] A sixth adjustment strategy for adjusting multiple antennas;

[0180] Adjustment goal: Use multi-antenna technologies (such as MIMO and beamforming) to enhance the stability and reliability of signal transmission;

[0181] Application scenarios: Suitable for scenarios requiring high reliability and high transmission rate;

[0182] The adjustment rules of the sixth adjustment strategy include:

[0183] When the predicted interference evaluation index weighted value is higher than the set 10th threshold, beamforming technology is enabled to focus the signal in the target direction to reduce interference;

[0184] When the predicted interference evaluation index weighted value is lower than the set 11th threshold, the MIMO technology is enabled to increase the data transmission rate.

[0185] For specific adjustment strategies and measures, please refer to the following table:

[0186]

[0187]

[0188] Table 1 Optimal interference adjustment strategy and adjustment measures

[0189] It should be noted that the various thresholds in this step need to be set according to actual data.

[0190] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A wireless IoT control method for electromechanical equipment based on multi-protocol adaptive conversion, characterized in that: include: Step 1: Automatically identify the communication protocol used by the electromechanical device by analyzing the format, header information and characteristic fields of the data packet, develop a parser for each communication protocol, and parse the data of different communication protocols into a unified intermediate format through the parser; Step 2: Collect electromagnetic signal data in the wireless communication environment, including signal strength, frequency, bandwidth, interference type, and channel quality, and clean, denoise, and normalize the collected raw data to remove invalid or abnormal data; Step three, extract the general features and protocol features related to interference, as well as the interference evaluation index data from the preprocessed data, build a LightGBM model with the general features and protocol features as input and the interference evaluation index weighted value as output, use the training set data to train the LightGBM model, and adjust the basic parameters of LightGBM until its performance index reaches the first expected value. Use the trained LightGBM model to output the importance score of each feature, and screen out the features within the set importance score threshold range as important features; Step 4: Constructing a neural network prediction model with the important features as input and the interference evaluation index as output, using the collected historical data to train the neural network prediction model until its prediction accuracy reaches a second expected value, and using the trained neural network prediction model to input the prediction result of the interference evaluation index at the next moment; Step 5: define an interference adjustment strategy and corresponding adjustment rules, and select an optimal interference adjustment strategy for adjusting wireless communication system parameters based on a determination result of whether the interference prediction result triggers the adjustment rules.

2. The method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion according to claim 1, characterized in that: The common features include: Signal strength for evaluating signal quality; The signal-to-noise ratio is used to reflect the clarity of the signal in a noisy environment; Interference intensity used to assess the extent to which noise affects the signal; Spectrum occupancy rate, which reflects the usage of spectrum resources; Bit error rate used to reflect communication quality; Channel utilization, which reflects the busyness of the channel; The packet loss rate reflects the proportion of data packets lost during transmission; The modulation and demodulation method used; Transmission distance used to reflect the physical distance between devices; and a timestamp.

3. The method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion according to claim 1, characterized in that: The protocol features include Modbus protocol features, Profibus protocol features, DLT645 protocol features and ZigBee protocol features; wherein, The Modbus protocol features include: A register address for identifying the location where data is stored; Function code for specifying the type of operation; The Modbus protocol data frame format is as follows: the structure of the Modbus data frame includes a start bit, an address field, a function code field, a data field, and a check bit; The Profibus protocol features include: A frame type used to indicate the type of data frame; Device address used to identify the device address in the Profibus network; Transport protocols; The DLT645 protocol features include: A meter address used to identify the address of an electric meter or other device; The DLT645 protocol data frame format is as follows: The structure of the DLT645 data frame includes a frame header, an address field, a control code, a data field, and a check bit; Code control code used to specify the type of operation; The ZigBee protocol features include: The network address used to identify the device address in the ZigBee network; PAN ID, a unique identifier used to identify the ZigBee network; Transfer rate.

4. The method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion according to claim 1, characterized in that: The interference evaluation indicators include: Interference intensity is used to evaluate the impact of interference signals on useful signals; Interference probability, which reflects the probability of interference occurring within a specific time period; Interference type used to reflect how unwanted signals affect wanted signals; The calculation method of the weighted value of interference evaluation index is: In the formula, Ie -weighting is the weighted value of interference evaluation index; Ie j is the j-th interference evaluation index value; is the weight of the j-th interference evaluation index, and 5. The method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion according to claim 1, characterized in that: The interference adjustment strategy includes: a first adjustment strategy for adjusting the communication channel; The adjustment rules of the first adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set first threshold, switching to the communication channel with the smallest predicted interference evaluation index weighted value; a second adjustment strategy for adjusting transmit power; The adjustment rules of the second adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set second threshold, the transmit power is increased to enhance the signal strength; When the predicted interference evaluation index weighted value is lower than the set third threshold, the transmit power is reduced to save energy and reduce interference to other devices; A third adjustment strategy for adjusting the modulation mode; The adjustment rules of the third adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set fourth threshold, switch to a modulation mode with stronger anti-interference capability; When the predicted interference evaluation index weighted value is lower than the set fifth threshold, switch to a higher-order modulation mode to increase the data transmission rate; A fourth adjustment strategy for adjusting the size of data packets; The adjustment rules of the fourth adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set sixth threshold, the data packet size is reduced to reduce transmission errors and retransmission probability; When the predicted interference evaluation index weighted value is lower than the set seventh threshold, the data packet size is increased to improve transmission efficiency; A fifth adjustment strategy for adjusting the transmission rate; The adjustment rules of the fifth adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set eighth threshold, the transmission rate is reduced to reduce the bit error rate; When the predicted interference evaluation index weighted value is lower than the set 9th threshold, the transmission rate is increased to improve the system throughput; A sixth adjustment strategy for adjusting multiple antennas; The adjustment rules of the sixth adjustment strategy include: When the predicted interference evaluation index weighted value is higher than the set 10th threshold, beamforming technology is enabled to focus the signal in the target direction to reduce interference; When the predicted interference evaluation index weighted value is lower than the set 11th threshold, the MIMO technology is enabled to increase the data transmission rate.

6. The method for controlling wireless Internet of Things of electromechanical equipment based on multi-protocol adaptive conversion according to claim 1, characterized in that: The neural network prediction model is a BP neural network prediction model with a three-layer structure including an input layer, an output layer and an output layer, wherein the number of neurons in the input layer is equal to the number of input features; the number of neurons in the output layer is equal to the number of types of output interference evaluation indicators.

7. A wireless IoT control system for electromechanical equipment based on multi-protocol adaptive conversion, characterized in that: The system adopts a layered architecture, including: The device layer includes various electromechanical devices that support Modbus, Profibus, DLT645, ZigBee, and Wi-Fi communication protocols; The protocol conversion layer is responsible for identifying and converting the communication protocols of different devices and realizing adaptive conversion of protocols. The perception layer is used to collect electromagnetic signal data in the wireless communication environment, including signal strength, frequency, bandwidth, interference type and channel quality; The data processing layer is used to preprocess, extract features and perform preliminary analysis on the collected data. Intelligent analysis layer: used to analyze data, predict interference and optimize communication parameters; Application layer: provides user interface and control functions to realize remote monitoring and management of equipment.

8. The wireless Internet of Things control system for electromechanical equipment based on multi-protocol adaptive conversion according to claim 7 is characterized in that: The protocol conversion layer includes The communication protocol identification submodule is used to automatically identify the communication protocol used by the electromechanical device by analyzing the format, header information and characteristic fields of the data packet; A parser module, wherein the parser module integrates several parsers for different communication protocols, and parses the data of different communication protocols into a unified intermediate format through the parsers; The perception layer includes: The data acquisition submodule is used to collect electromagnetic signal data including signal strength, frequency, bandwidth, interference type and channel quality in the wireless communication environment; The data processing layer includes: The data processing submodule is used to clean, denoise, and normalize the collected raw data to remove invalid or abnormal data; Feature extraction submodule, used to extract general features and protocol features related to interference, as well as interference evaluation indicators from the preprocessed data; The LightGBM model construction submodule is used to build a LightGBM model with general features and protocol features as input and the weighted value of interference evaluation index as output; The LightGBM model training submodule is used to train the LightGBM model using the training set data and adjust the basic parameters of LightGBM until its performance index reaches the first expected value; The feature importance score output submodule is used to output the importance score of each feature using the trained LightGBM model; The feature screening submodule is used to screen out features within a set importance score threshold as important features; The intelligent analysis layer includes: A neural network prediction model construction submodule is used to construct a neural network prediction model with the important features as input and the interference evaluation index as output; A neural network prediction model training submodule is used to train the neural network prediction model using the collected historical data until its prediction accuracy reaches a second expected value; The prediction result output submodule is used to input the prediction result of the interference evaluation index at the next moment using the trained neural network prediction model; The adjustment strategy definition submodule is used to define the interference adjustment strategy and the corresponding adjustment rules; An adjustment strategy selection submodule, configured to select an optimal interference adjustment strategy for adjusting wireless communication system parameters based on a determination result of whether the interference prediction result triggers the adjustment rule; The application layer includes: The device control submodule is used to provide a user interface and control functions to achieve remote monitoring and management of the device.

9. The electromechanical equipment wireless IoT control system based on multi-protocol adaptive conversion according to claim 7, characterized in that: The control system also includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, is capable of implementing the steps of the method for wireless Internet of Things control of electromechanical equipment based on multi-protocol adaptive conversion as described in any one of claims 1-6.

Images