Control method and system for mining full-localization PLC equipment

Abstract

The invention relates to a control method and system for mining full-localization PLC equipment, belongs to the technical field of mining equipment control, and solves the problem that explosion-proof safety, efficient communication and intelligent maintenance are difficult to completely meet in the prior art. Comprising the following steps: analyzing mine characteristic data by acquiring the mine characteristic data of a mine explosive environment, and installing PLC equipment in a mine according to an analysis result; the method comprises the following steps: establishing a BP equipment state prediction model, optimizing parameters in the BP equipment state prediction model by using a POS particle swarm algorithm, inputting training equipment data into the POS-BP equipment state prediction model for prediction, adjusting the parameters of PLC equipment according to the mine equipment state, obtaining adjusted target equipment data, and outputting the adjusted target equipment data. And judging whether the target equipment data reaches a safe state, and if the target equipment data does not reach the safe state, triggering preventive maintenance measures. According to the invention, potential faults are identified in advance and preventive maintenance measures are automatically triggered.

Description

Technical Field

[0001] The present invention belongs to the technical field of mining equipment control, and in particular relates to a control method and system for a mining-based fully domestically produced PLC device. Background Art

[0002] In the context of the continuous advancement of mining automation, the particularity of the mine operating environment, especially its explosive characteristics, has put forward extremely high safety and technical requirements for automation control equipment. The application of domestically produced PLC equipment in the mining field has become an inevitable trend. However, the special mining environment requires the equipment to have good explosion-proof performance, stable data transmission capabilities and strong field adaptability. Traditional PLC equipment often finds it difficult to fully meet the needs of explosion-proof safety, efficient communication and intelligent maintenance when facing such complex environments. Therefore, how to efficiently control PLC equipment in mines in real time and ensure its operational stability is a technical problem that needs to be solved urgently at this stage. Summary of the invention

[0003] In view of the above analysis, the embodiments of the present invention aim to provide a control method and system for domestically produced PLC equipment for mining, so as to solve the technical problems in the prior art that are difficult to fully meet the requirements of explosion-proof safety, efficient communication and intelligent maintenance.

[0004] The object of the present invention is achieved in that:

[0005] A control method for a domestically produced PLC device for mining, comprising the following steps:

[0006] Acquire mine characteristic data of the explosive environment of the mine, analyze the mine characteristic data, and install PLC equipment in the mine according to the analysis results;

[0007] Acquire real-time device data in the PLC device, perform data preprocessing on the real-time device data, and obtain training device data;

[0008] Establishing a BP equipment state prediction model based on a BP neural network, optimizing the parameters in the BP equipment state prediction model using a POS particle swarm algorithm, and obtaining a POS-BP equipment state prediction model;

[0009] Inputting the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status;

[0010] The parameters of the PLC device are adjusted according to the mine equipment status, the adjusted target device data is obtained, and it is determined whether the target device data reaches a safe state. If it does not reach a safe state, preventive maintenance measures are triggered.

[0011] Further, the obtaining of mine characteristic data of the explosive environment of the mine, analyzing the mine characteristic data, and installing the PLC device in the mine according to the analysis result includes:

[0012] Use gas detectors and thermometers and hygrometers to measure the methane concentration data, oxygen concentration data, temperature data and humidity data in the mine, and record the mine structure information and mine ventilation information to obtain mine characteristic data; use a linear regression algorithm to analyze the mine characteristic data to obtain the mine environmental stability, explosion risk level, and ventilation efficiency; evaluate the environmental adaptability requirements of PLC equipment in different areas based on the analysis results, including explosion-proof level, temperature and humidity resistance; select the PLC equipment model for the mine environment based on the evaluation results, and calculate the installation location and method; install the PLC equipment based on the installation location and method, and conduct preliminary functional tests and environmental adaptability tests.

[0013] Furthermore, the acquiring of real-time device data in the PLC device and preprocessing of the real-time device data to obtain training device data includes:

[0014] The temperature data, vibration data, current data, voltage data, environmental parameters and control signal data of the equipment are collected in real time through the built-in sensors of the PLC equipment to obtain real-time equipment data; abnormal values ​​and duplicate values ​​in the real-time equipment data are deleted, missing data are filled, and the data format is unified to obtain standard real-time equipment data; features related to the standard real-time equipment data and the equipment status are extracted to obtain feature real-time equipment data; the feature real-time equipment data is standardized or normalized to obtain training equipment data.

[0015] Furthermore, the BP device state prediction model is established based on the BP neural network, and the parameters in the BP device state prediction model are optimized using the POS particle swarm algorithm to obtain the POS-BP device state prediction model, including:

[0016] A BP device state prediction model is established based on a BP neural network, the neural network is initialized, and the structures of each layer of the BP neural network are determined; the population is initialized, the size and dimension of the population are determined, the speed and position of the particles are initialized, and the number of iterations is set; the particle fitness value is calculated, and the root mean square error is used as the fitness function of the BP device state prediction model; the particle population is iterated, the particle speed and position are updated, and a new population is obtained. The particles in the new population are first cross-operated with probability P1, and then the particles with poor fitness values ​​are mutated with probability P2; individual extreme values, group extreme values ​​and optimal fitness values ​​are updated. If the number of algorithm iterations is less than the specified error, the iteration is stopped and the result is obtained; the weight threshold of the BP device state prediction model is initialized using the result to obtain a POS-BP device state prediction model.

[0017] Furthermore, the inputting of the training equipment data into the POS-BP equipment status prediction model to perform prediction to obtain the mine equipment status includes:

[0018] The training equipment data is input into the POS-BP equipment state prediction model for training; the number of iterations is set to 1000 times, the number of input layers of the POS-BP equipment state prediction model is 10, the number of hidden layers is 7, and the number of output layers is 1; the error between the predicted value and the actual output is calculated, and the weight and threshold are updated according to the error to obtain the mine equipment state.

[0019] Further, the parameters of the PLC device are adjusted according to the mine equipment status, the adjusted target device data is obtained, and it is determined whether the target device data reaches a safe state. If the safe state is not reached, a preventive maintenance measure is triggered, including:

[0020] Generate PLC equipment adjustment instructions based on the status of mine equipment, and the PLC equipment adjustment instructions at least include operating frequency and load distribution; collect actual operating data of the adjusted equipment, compare safety thresholds and optimal operating status indicators, and determine whether a safe and efficient operating state is achieved; if the equipment status still does not meet safety standards after adjusting parameters, automatically trigger preventive maintenance measures and generate self-healing control logic.

[0021] Furthermore, in a control system of a domestically produced PLC device for mining, the control system of the PLC device includes the following modules:

[0022] An equipment installation module, used to obtain mine characteristic data of the explosive environment of the mine, analyze the mine characteristic data, and install the PLC equipment in the mine according to the analysis results;

[0023] A data processing module is used to obtain real-time device data in the PLC device, perform data preprocessing on the real-time device data, and obtain training device data;

[0024] A model building module is used to build a BP device state prediction model based on a BP neural network, and optimize the parameters in the BP device state prediction model using a POS particle swarm algorithm to obtain a POS-BP device state prediction model;

[0025] An equipment prediction module, used for inputting the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status;

[0026] The equipment adjustment module is used to adjust the parameters of the PLC equipment according to the mine equipment status, obtain the adjusted target equipment data, and determine whether the target equipment data has reached a safe state. If it has not reached a safe state, preventive maintenance measures are triggered.

[0027] Furthermore, the control system of the PLC device includes the following submodules:

[0028] The collection submodule is used to collect the temperature data, vibration data, current data, voltage data, environmental parameters and control signal data of the device in real time through the built-in sensors of the PLC device to obtain real-time device data;

[0029] A deletion submodule is used to delete abnormal values ​​and duplicate values ​​in the real-time device data, fill in missing data, unify the data format, and obtain standard real-time device data;

[0030] An extraction submodule, used to extract features related to the standard real-time device data and the device state to obtain feature real-time device data;

[0031] The normalization submodule is used to standardize or normalize the characteristic real-time device data to obtain training device data.

[0032] Furthermore, the control system of the PLC device includes the following submodules:

[0033] An input submodule, used for inputting the training device data into the POS-BP device state prediction model for training;

[0034] A submodule is set to set the number of iterations to 1000, the number of input layers of the POS-BP device state prediction model to 10, the number of hidden layers to 7, and the number of output layers to 1;

[0035] The calculation submodule is used to calculate the error between the predicted value and the actual output, update the weight and threshold according to the error, and obtain the mine equipment status.

[0036] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0037] By acquiring the mine characteristic data of the explosive environment of the mine, analyzing the mine characteristic data, and installing the PLC equipment in the mine according to the analysis results; acquiring the real-time equipment data in the PLC equipment, preprocessing the real-time equipment data, and obtaining the training equipment data; establishing a BP equipment state prediction model based on the BP neural network, and optimizing the parameters in the BP equipment state prediction model using the POS particle swarm algorithm to obtain the POS-BP equipment state prediction model; inputting the training equipment data into the POS-BP equipment state prediction model for prediction to obtain the mine equipment state; adjusting the parameters of the PLC equipment according to the mine equipment state, obtaining the adjusted target equipment data, and judging whether the target equipment data has reached a safe state. If it has not reached a safe state, triggering preventive maintenance measures. Potential faults can be identified in advance and preventive maintenance measures can be automatically triggered. At the same time, self-healing control logic is designed so that the equipment can automatically resume operation in a minor fault state, reducing downtime. It not only solves the urgent demand of the mining industry for domestic high-end control equipment, but also significantly improves the comprehensive performance and application value of mining PLC equipment by integrating domestic core technologies and intelligent functions. This method can effectively improve the automation level, operation safety and production efficiency of mining operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0039] Figure 1 The present invention provides a control method for a domestically produced PLC device for mining Figure 1 ;

[0040] Figure 2 The present invention provides a control method for a domestically produced PLC device for mining Figure 2 ;

[0041] Figure 3 A schematic diagram of a control system of a domestically produced PLC device for mining provided by the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments disclosed in this disclosure can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0043] In the accompanying drawings, the size and relative size of components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments may be implemented differently, a specific process sequence may be performed in a different order than described. For example, two successively described processes may be performed substantially simultaneously or in an order opposite to the order described. In addition, the same reference numerals represent the same components.

[0044] Example 1

[0045] The present invention will be described in detail below in conjunction with the accompanying drawings. Figure 1 As shown, a control method for a domestically produced PLC device for a mine, the control method for the PLC device comprises the following steps:

[0046] Step 101, obtaining mine characteristic data of the explosive environment of the mine, analyzing the mine characteristic data, and installing PLC equipment in the mine according to the analysis results;

[0047] Specifically, in this embodiment, a gas detector and a thermometer and hygrometer are used to measure the methane concentration data, oxygen concentration data, temperature data and humidity data in the mine, and the mine structure information and ventilation mine condition information are recorded to obtain mine characteristic data; a linear regression algorithm is used to analyze the mine characteristic data to obtain the mine environmental stability, explosion risk level, and ventilation efficiency; based on the analysis results, the environmental adaptability requirements of PLC equipment in different regions are evaluated, including explosion-proof level, temperature and humidity resistance; based on the evaluation results, the PLC equipment model for the mine environment is selected, and the installation location and method are calculated; based on the installation location and method, the PLC equipment is installed, and preliminary functional testing and environmental adaptability testing are carried out.

[0048] Exemplarily, the mine characteristic data includes at least:

[0049] Geological data: geological structure (faults, folds, etc.), distribution of mineral deposits, ore properties (composition, hardness, structure, etc.), rock formation characteristics (stability, permeability, etc.);

[0050] Environmental monitoring data: temperature, humidity, gas concentration (such as methane, carbon dioxide, oxygen, etc.), noise level, radiation level, vibration;

[0051] Equipment operation data: equipment performance parameters (power, efficiency, etc.), operating status (start and stop records, fault alarms, etc.), maintenance records (repairs, maintenance, etc.).

[0052] The computer acquires data every half an hour and records the mine structure information and mine ventilation information.

[0053] Mine structure information includes at least:

[0054] Ventilation network structure: distribution and connection of branch lanes, location, size and direction of main ventilation channels, and the relationship between various ventilation channels;

[0055] Mining area layout: location and shape of the mining face, direction of advancement of the working face, and regional division of the mine at different mining stages;

[0056] Layout of auxiliary facilities: layout of ventilation lanes and transport lanes, location and structure of lifting shafts and transport shafts, location and configuration of power supply, drainage, communication and other infrastructure;

[0057] Support conditions: support types (such as anchors, shotcrete, steel frames, etc.) and their distribution, support materials and structural characteristics;

[0058] Geological conditions: geological structure of the area where the mine is located, assessment of formation stability, location of fault zones and weak layers.

[0059] Mine ventilation information shall include at least:

[0060] Ventilation method: Central type: the main ventilation shaft is located in the center of the mine; Diagonal type: the main ventilation shaft is located in a corner of the mine, usually two ventilation shafts; Hybrid type: combines the advantages of central and diagonal types, suitable for large mines;

[0061] Ventilation method: Extraction type: The air in the well is extracted through the ventilator to form negative pressure ventilation; Pressure type: Fresh air is pressed into the well through the ventilator to form positive pressure ventilation;

[0062] Ventilation network: direction and flow of airflow; location and status of dampers, wind bridges and other regulating devices;

[0063] Air quality monitoring: concentration of toxic and harmful gases (such as methane, carbon monoxide, sulfur dioxide, etc.); dust content, temperature and humidity levels in the air;

[0064] Ventilation equipment status: operating status of the ventilator, wind speed measurement data, and working conditions of the air volume adjustment device;

[0065] Emergency ventilation system: location of emergency ventilation passages, status of backup ventilation equipment, emergency ventilation plan and operating procedures.

[0066] Integration of domestic chips and operating systems: We use domestically developed high-performance embedded processors and stable and reliable real-time operating systems as the basis of PLC hardware and software to ensure the comprehensive localization of equipment from the bottom layer to the application layer, and enhance information security and supply chain stability.

[0067] Enhanced explosion-proof design: Aiming at the explosive environment of mines, the shell structure and internal layout of the PLC equipment are innovatively designed, and new flame-retardant materials and explosion-proof structures are used to ensure the safe operation of the equipment under extreme conditions, in compliance with national explosion-proof standards.

[0068] Converged communication technology: Integrates modules compatible with a variety of domestic communication protocols, such as industrial Ethernet based on Loongson CPU and Beidou satellite communication technology, to achieve high-speed, low-latency, and highly reliable data transmission between ground and underground equipment, and maintain stable communication even in complex mining environments.

[0069] In this embodiment, the linear regression algorithm is used to analyze the mine characteristic data to obtain the mine environmental stability, explosion risk level, and ventilation efficiency, including the following steps:

[0070] (I) Data Collection:

[0071] Geological data: rock stability, ore properties, etc.; environmental monitoring data: temperature, humidity, gas concentration, etc.; ventilation data: wind speed, air volume, ventilation efficiency, etc.

[0072] (II) Data preprocessing:

[0073] Data cleaning: remove invalid or erroneous data points, handle missing values: use interpolation methods to fill missing values, standardization / normalization: make the data on the same scale to avoid excessive influence of certain features.

[0074] (III) Feature selection: Correlation analysis: Calculate the correlation coefficient between each feature and the target variable; Feature importance ranking: Use statistical tests or models (such as Lasso regression) to determine important features; Feature subset selection: Select the feature combination that best represents the characteristics of the mine.

[0075] (IV) Model training: Linear regression model: Construct a multivariate linear regression model and use the selected features to predict the target variable; Model training: Divide the preprocessed data into a training set and a test set, and use the training set to train the model; Hyperparameter tuning: Adjust the model parameters to obtain better performance.

[0076] (V) Model evaluation: Cross-validation: Use cross-validation techniques to evaluate the generalization ability of the model; Performance indicators: Calculate mean square error (MSE), coefficient of determination (R2) and other evaluation indicators; Result visualization: Draw a scatter plot or error distribution diagram between the predicted results and the actual values.

[0077] (VI) Result interpretation: Mine environmental stability: Evaluate the stability of the mine structure based on the model prediction results; Explosion risk level: Predict the probability of explosion risk based on factors such as gas concentration; Ventilation efficiency: Calculate the effectiveness and efficiency of the ventilation system.

[0078] The model prediction results include mine environmental stability, explosion risk level, and ventilation efficiency.

[0079] In this embodiment, the mining equipment includes:

[0080] Lifting equipment: lifting containers (such as cages, buckets, mine cars and man-cars), lifting wire ropes, and hoists;

[0081] Ventilation equipment: main fan, local ventilator, ventilation duct;

[0082] Compressed air equipment: air compressor, compressed air pipeline;

[0083] Pressure equipment: various pressure vessels;

[0084] Drainage equipment: water pump, drainage pipe;

[0085] Mining equipment: coal mining machines, roadheaders, drilling machines, crushers, loaders;

[0086] Support equipment: anchor drilling rig, anchor cable drilling rig, support;

[0087] Transportation equipment: mining cars, electric locomotives, belt conveyors, rails;

[0088] Power supply and electrical equipment: transformers, switchgear, cables;

[0089] Lighting equipment;

[0090] Safety monitoring and gas extraction equipment: sensors, monitoring systems, extraction pumps, gas detectors.

[0091] Step 102: acquiring real-time device data in the PLC device, performing data preprocessing on the real-time device data, and obtaining training device data;

[0092] Specifically, in this embodiment, the temperature data, vibration data, current data, voltage data, environmental parameters and control signal data of the device are collected in real time through the built-in sensors of the PLC device to obtain real-time device data; abnormal values ​​and duplicate values ​​in the real-time device data are deleted, missing data are filled, and the data format is unified to obtain standard real-time device data; features related to the standard real-time device data and the device status are extracted to obtain feature real-time device data; the feature real-time device data is standardized or normalized to obtain training device data.

[0093] Step 103: Establish a BP device state prediction model based on the BP neural network, and use the POS particle swarm algorithm to optimize the parameters in the BP device state prediction model to obtain a POS-BP device state prediction model;

[0094] Specifically, in this embodiment, a BP device state prediction model is established based on a BP neural network, the neural network is initialized, and the structure of each layer of the BP neural network is determined; the population is initialized, the size and dimension of the population are determined, the speed and position of the particles are initialized, and the number of iterations is set; the particle fitness value is calculated, and the root mean square error is used as the fitness function of the BP device state prediction model; the particle group is iterated, the particle speed and position are updated, and a new population is obtained. The particles in the new population are first cross-operated with probability P1, and then the particles with poor fitness values ​​are mutated with probability P2; individual extreme values, group extreme values ​​and optimal fitness values ​​are updated. If the number of algorithm iterations is less than the specified error, the iteration is stopped and the result is obtained; the weight threshold of the BP device state prediction model is initialized using the result to obtain the POS-BP device state prediction model.

[0095] Step 104: input the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status;

[0096] Specifically, in this embodiment, the training equipment data is input into the POS-BP equipment state prediction model for training; the number of iterations is set to 1000 times, the number of input layers of the POS-BP equipment state prediction model is 10, the number of hidden layers is 7, and the output layer is 1; the error between the predicted value and the actual output is calculated, and the weight and threshold are updated according to the error to obtain the mine equipment status.

[0097] Step 105: adjust the parameters of the PLC device according to the mine equipment status, obtain the adjusted target device data, and determine whether the target device data has reached a safe state. If it has not reached a safe state, trigger preventive maintenance measures.

[0098] Specifically, in this embodiment, PLC equipment adjustment instructions are generated according to the status of mine equipment, and the PLC equipment adjustment instructions include at least operating frequency and load distribution; the actual operating data of the adjusted equipment is collected, and the safety threshold and the optimal operating status index are compared to determine whether a safe and efficient operating state is achieved; if the equipment status still does not meet the safety standards after adjusting the parameters, preventive maintenance measures are automatically triggered, and self-healing control logic is generated at the same time.

[0099] Specifically, the target equipment in this embodiment is various mine equipment in the mine, such as safety monitoring and gas extraction equipment, compressed air equipment, pressure equipment, drainage equipment, mining equipment, support equipment, and transportation equipment.

[0100] Specifically, in this embodiment, the preventive maintenance measures are automatically triggered and the self-healing control logic is generated, including the following contents:

[0101] Algorithms and models: Use machine learning and statistical analysis algorithms to predict equipment failures, such as predicting motor bearing failures based on trend analysis of historical data. Alerts and notifications: Once a potential problem is detected, the PLC can automatically send an alert to the maintenance team, or even directly to the mobile device or SCADA system to schedule maintenance in advance. Adaptive control: Redundancy and switching: Set hardware redundancy (such as dual CPU, network redundancy), and automatically switch to the backup system when the main device fails to ensure continuous operation. Fault avoidance logic: Programming implements fault avoidance strategies. When it detects that a component is about to exceed the safe operating range, the PLC automatically adjusts the control logic to avoid failures.

[0102] Specifically, the self-healing control logic in this implementation includes: Self-repair function: Software restart: For certain software errors or temporary failures, the PLC can automatically restart the application or service and try to restore to normal operating state. Backup and recovery: Regularly and automatically back up configurations and programs to non-volatile storage, and automatically or manually restore to the most recent normal configuration after a failure. Remote management and upgrade: Remote monitoring: Through a network connection, operation and maintenance personnel can monitor the status of the PLC in the control room or remote location, reducing the need for on-site inspections. Firmware and software updates: Support automatic detection and installation of security patches and software updates to reduce failures caused by software defects. Energy management: Intelligent energy-saving mode: Dynamically adjust energy consumption according to production needs and equipment status, such as reducing the power of non-critical equipment during off-peak hours.

[0103] Its beneficial effects are that by acquiring the mine characteristic data of the explosive environment of the mine, the mine characteristic data is analyzed, and the PLC equipment in the mine is installed according to the analysis results; the real-time equipment data in the PLC equipment is acquired, and the real-time equipment data is preprocessed to obtain the training equipment data; the BP equipment state prediction model is established based on the BP neural network, and the parameters in the BP equipment state prediction model are optimized by using the POS particle swarm algorithm to obtain the POS-BP equipment state prediction model; the training equipment data is input into the POS-BP equipment state prediction model for prediction to obtain the mine equipment state; the parameters of the PLC equipment are adjusted according to the mine equipment state, and the adjusted target equipment data is obtained to determine whether the target equipment data has reached a safe state. If it has not reached a safe state, preventive maintenance measures are triggered. Potential faults can be identified in advance and preventive maintenance measures can be automatically triggered. At the same time, self-healing control logic is designed so that the equipment can automatically resume operation in a minor fault state, reducing downtime. It not only solves the urgent demand of the mining industry for domestic high-end control equipment, but also significantly improves the comprehensive performance and application value of mining PLC equipment by integrating domestic core technologies and intelligent functions. This method can effectively improve the automation level, operation safety and production efficiency of mining operations.

[0104] See also Figure 2 In a control method for a domestically produced PLC device for a mine, obtaining real-time device data in the PLC device, performing data preprocessing on the real-time device data, and obtaining training device data include the following steps:

[0105] Step 201: collect temperature data, vibration data, current data, voltage data, environmental parameters and control signal data of the device in real time through the built-in sensors of the PLC device to obtain real-time device data;

[0106] Step 202: Delete abnormal values ​​and duplicate values ​​in the real-time device data, fill in missing data, unify the data format, and obtain standard real-time device data;

[0107] Step 203: extracting features related to the standard real-time device data and the device status to obtain feature real-time device data;

[0108] Step 204: standardize or normalize the characteristic real-time device data to obtain training device data.

[0109] The above is an introduction to the embodiment of the control method of a domestically produced PLC device for mining. Figure 3 In a control system of a domestically produced PLC equipment for mining, the coordination and optimization system includes the following modules:

[0110] Equipment installation module, used to obtain mine characteristic data of explosive environment in mines, analyze the mine characteristic data, and install PLC equipment in mines according to the analysis results;

[0111] A data processing module is used to obtain real-time device data in the PLC device, perform data preprocessing on the real-time device data, and obtain training device data;

[0112] The model building module is used to build a BP equipment state prediction model based on the BP neural network, and optimize the parameters in the BP equipment state prediction model using the POS particle swarm algorithm to obtain a POS-BP equipment state prediction model;

[0113] The equipment prediction module is used to input the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status;

[0114] The equipment adjustment module is used to adjust the parameters of the PLC equipment according to the status of the mine equipment, obtain the adjusted target equipment data, and determine whether the target equipment data has reached a safe state. If it has not reached a safe state, preventive maintenance measures are triggered.

[0115] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A control method for a domestically produced PLC device for mining, characterized in that: The control method of the PLC device comprises the following steps: Acquire mine characteristic data of the explosive environment of the mine, analyze the mine characteristic data, and install PLC equipment in the mine according to the analysis results; Acquire real-time device data in the PLC device, perform data preprocessing on the real-time device data, and obtain training device data; Establishing a BP equipment state prediction model based on a BP neural network, optimizing the parameters in the BP equipment state prediction model using a POS particle swarm algorithm, and obtaining a POS-BP equipment state prediction model; Inputting the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status; The parameters of the PLC device are adjusted according to the mine equipment status, the adjusted target device data is obtained, and it is determined whether the target device data reaches a safe state. If it does not reach a safe state, preventive maintenance measures are triggered.

2. The control method of the domestically produced PLC equipment for mining according to claim 1 is characterized in that: The method of obtaining the mine characteristic data of the explosive environment of the mine, analyzing the mine characteristic data, and installing the PLC device in the mine according to the analysis result includes: Use gas detectors and thermometers to measure the methane concentration data, oxygen concentration data, temperature data and humidity data in the mine, and record the mine structure information and mine ventilation information to obtain mine characteristic data; The mine characteristic data is analyzed using a linear regression algorithm to obtain the mine environmental stability, explosion risk level, and ventilation efficiency; Based on the analysis results, evaluate the environmental adaptability requirements of PLC equipment in different regions, including explosion-proof level, temperature and humidity resistance; Select the PLC equipment model for the mine environment based on the evaluation results, and calculate the installation location and method; Install PLC equipment based on the installation location and method, and conduct preliminary functional tests and environmental adaptability tests.

3. The control method of the domestically produced PLC equipment for mining according to claim 1 is characterized in that: The step of acquiring the real-time device data in the PLC device and performing data preprocessing on the real-time device data to obtain training device data includes: The built-in sensors of the PLC equipment collect the equipment's temperature data, vibration data, current data, voltage data, environmental parameters and control signal data in real time to obtain real-time equipment data; Deleting abnormal values ​​and duplicate values ​​in the real-time device data, filling in missing data, unifying the data format, and obtaining standard real-time device data; Extracting features related to the standard real-time device data and the device state to obtain feature real-time device data; The characteristic real-time device data is standardized or normalized to obtain training device data.

4. The control method of the domestically produced PLC equipment for mining according to claim 1 is characterized in that: The BP device state prediction model is established based on the BP neural network, and the parameters in the BP device state prediction model are optimized using the POS particle swarm algorithm to obtain the POS-BP device state prediction model, including: Establish a BP equipment status prediction model based on the BP neural network, initialize the neural network, and determine the structure of each layer of the BP neural network; Initialize the population, determine the size and dimension of the population, initialize the speed and position of the particles, and set the number of iterations; Calculating the particle fitness value, and taking the root mean square error as the fitness function of the BP device state prediction model; Iterate the particle swarm, update the particle speed and position, and obtain a new population. The particles in the new population first perform a pairwise crossover operation with probability P1, and then perform a mutation operation on particles with poor fitness values ​​with probability P2; Update individual extreme values, group extreme values ​​and optimal fitness values. If the number of algorithm iterations is less than the specified error, stop the iteration and obtain the result. The result is used to initialize the weight threshold of the BP device state prediction model to obtain the POS-BP device state prediction model.

5. The control method of the domestically produced PLC equipment for mining according to claim 1 is characterized in that: The step of inputting the training equipment data into the POS-BP equipment status prediction model to perform prediction to obtain the mine equipment status includes: Inputting the training device data into the POS-BP device state prediction model for training; The number of iterations is set to 1000, the number of input layers of the POS-BP device status prediction model is 10, the number of hidden layers is 7, and the number of output layers is 1; Calculate the error between the predicted value and the actual output, update the weight and threshold according to the error, and get the mine equipment status.

6. The control method of the domestically produced PLC equipment for mining according to claim 1 is characterized in that: The adjusting of the parameters of the PLC device according to the mine equipment status, obtaining the adjusted target device data, judging whether the target device data reaches a safe state, and triggering preventive maintenance measures if the safe state is not reached, includes: Generate a PLC device adjustment instruction according to the mine equipment status, wherein the PLC device adjustment instruction at least includes an operating frequency and a load distribution; Collect the actual operating data of the adjusted equipment, compare the safety threshold and the optimal operating status indicators, and determine whether it has reached a safe and efficient operating state; If the equipment status still does not meet safety standards after adjusting the parameters, preventive maintenance measures are automatically triggered and self-healing control logic is generated.

7. A control system for a domestically produced PLC device for mining, characterized in that: The control system of the PLC device includes the following modules: An equipment installation module, used to obtain mine characteristic data of the explosive environment of the mine, analyze the mine characteristic data, and install the PLC equipment in the mine according to the analysis results; A data processing module is used to obtain real-time device data in the PLC device, perform data preprocessing on the real-time device data, and obtain training device data; A model building module is used to build a BP device state prediction model based on a BP neural network, and optimize the parameters in the BP device state prediction model using a POS particle swarm algorithm to obtain a POS-BP device state prediction model; An equipment prediction module, used for inputting the training equipment data into the POS-BP equipment status prediction model for prediction to obtain the mine equipment status; The equipment adjustment module is used to adjust the parameters of the PLC equipment according to the mine equipment status, obtain the adjusted target equipment data, and determine whether the target equipment data has reached a safe state. If it has not reached a safe state, preventive maintenance measures are triggered.

8. The control system of the domestically produced PLC equipment for mining according to claim 7 is characterized in that: The control system of the PLC device includes the following submodules: The collection submodule is used to collect the temperature data, vibration data, current data, voltage data, environmental parameters and control signal data of the device in real time through the built-in sensors of the PLC device to obtain real-time device data; A deletion submodule is used to delete abnormal values ​​and duplicate values ​​in the real-time device data, fill in missing data, unify the data format, and obtain standard real-time device data; An extraction submodule, used to extract features related to the standard real-time device data and the device state to obtain feature real-time device data; The normalization submodule is used to standardize or normalize the characteristic real-time device data to obtain training device data.

9. The control system of the domestically produced PLC equipment for mining according to claim 7 is characterized in that: The control system of the PLC device includes the following submodules: An input submodule, used for inputting the training device data into the POS-BP device state prediction model for training; A submodule is set to set the number of iterations to 1000, the number of input layers of the POS-BP device state prediction model to 10, the number of hidden layers to 7, and the number of output layers to 1; The calculation submodule is used to calculate the error between the predicted value and the actual output, update the weight and threshold according to the error, and obtain the mine equipment status.

Images