Coal mine intelligent comprehensive management and control system based on industrial internet

Abstract

The invention, which relates to the technical field of industrial Internet and energy management, discloses a coal mine intelligent comprehensive management and control system based on an industrial Internet, comprising a top management layer, a middle control layer and a bottom sensing layer. The bottom sensing layer is used for collecting electric power parameters, monitoring equipment states, executing control instructions and uploading real-time operation data to the middle control layer; the middle control layer receives the data of the bottom sensing layer, is a regional energy control node, is responsible for executing local power supply optimization, load balancing management and fault early warning processing, and gathers and transmits regional state information to the top management layer; and the top management layer receives the summarized information, carries out global strategy making, system state monitoring and cross-regional resource allocation, and issues a global strategy to the middle control layer to execute a new round of management and control. Through cooperative work of the top layer, the middle layer and the bottom layer, global optimization and local dynamic allocation of the coal mine power supply system are achieved, and energy waste and power supply imbalance are avoided.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet and energy management technology, and in particular to an intelligent comprehensive management and control system for coal mines based on industrial Internet. Background Art

[0002] The production and operation environment of coal mines is complex, and the demand for energy is large and unevenly distributed. The main manifestations are large fluctuations in the power load of underground mining, transportation, ventilation and other equipment, frequent short-term power shocks, significant differences in power demand in different areas and at different times, and frequent equipment start-up and shutdown resulting in fluctuations in power quality. At the same time, underground lighting, drainage and other infrastructure require continuous and stable power supply. Traditional energy management systems are mainly based on centralized control, with slow response speed, lack of real-time load forecasting and dynamic adjustment capabilities, incomplete energy usage data collection and insufficient analysis depth, and information islands formed between systems that are difficult to coordinate and optimize. In addition, the power supply system has safety hazards such as untimely fault warnings and insufficient switching of backup power supplies for important equipment. Existing technologies lack intelligent and distributed control methods for energy, making it difficult to achieve precise control and optimization of various areas in coal mines. A new energy management solution is urgently needed.

[0003] In view of the complex energy demand characteristics of coal mines, the technical solutions currently adopted by the industry mainly include traditional centralized energy management systems (EMS) and PLC-based automatic control systems. These systems realize basic data collection, monitoring and control functions by installing various sensors and actuators. However, due to the rigid system architecture and insufficient intelligence, there are many limitations in practical applications: the monitoring system has a delayed response and cannot respond to sudden load changes in a timely manner; the energy consumption data collection coverage is not comprehensive, and there is a lack of in-depth mining and analysis; the synergy between the subsystems is poor, and it is difficult to achieve global optimization scheduling; the fault warning mechanism is simple and mainly relies on manual experience judgment; the power supply system has insufficient redundancy and limited emergency response capabilities. These technologies are difficult to meet the needs of modern coal mines for intelligent and refined energy management, and cannot effectively solve problems such as low energy efficiency and imbalance between supply and demand. Therefore, it is urgent to develop a new generation of intelligent distributed energy management technology to improve the level of coal mine energy management. Summary of the invention

[0004] In view of the problems existing in the existing industrial Internet coal mine intelligent comprehensive management and control system, the present invention proposes a coal mine intelligent comprehensive management and control system based on the industrial Internet.

[0005] Therefore, the problem to be solved by the present invention is the lack of intelligent control means for energy, making it difficult to achieve precise control and optimization of various areas within a coal mine.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an intelligent comprehensive management and control system for coal mines based on the industrial Internet, which includes a top-level management layer, a middle-level control layer and a bottom-level perception layer; the bottom-level perception layer is responsible for power parameter collection, equipment status monitoring, and execution of control instructions, and uploading real-time operation data to the middle-level control layer; the middle-level control layer receives the data from the bottom-level perception layer, is a regional energy control node, and is responsible for performing local power supply optimization, load balancing management, and fault warning processing, and aggregating and transmitting regional status information to the top-level management layer; the top-level management layer receives the aggregated information, formulates global strategies, monitors system status, and allocates cross-regional resources, and sends the global strategies to the middle-level control layer to execute a new round of management and control.

[0008] As a preferred solution of the coal mine intelligent comprehensive management and control system based on industrial Internet described in the present invention, the bottom perception layer collects the operating status and power parameters of the equipment in real time through sensors, including voltage, current, power factor, temperature, vibration and speed, and transmits the data to the edge computing node for local processing and analysis; the local processing adopts the detection model of support vector machine SVM, and the classification decision function of the detection model is expressed as:

[0009] f(x)=w T x+b

[0010] Among them, x = [I, V, P, T, X] is a feature vector representing the sensor data at the current moment, I represents current, V represents voltage, P represents power, T represents temperature, X represents vibration, w is the weight vector, b is the bias term, and f(x) is the output of the decision function.

[0011] As a preferred solution of the coal mine intelligent comprehensive management and control system based on industrial Internet described in the present invention, the SVM model is trained to minimize the number of samples with classification errors by adjusting the weight w and the bias b, which is expressed as:

[0012]

[0013] Among them, ||w|| 2 is the regularization term of the weight, C is the penalty parameter, which controls the tolerance of the model to misclassified samples, ξ i is a slack variable, which indicates the classification error of sample i, and n is the number of samples. The local edge node calculation data is processed based on the trained SVM model. If it is judged to be a "fault state", an alarm is triggered to notify the operator, and the fault information is uploaded to the middle control layer. The middle control layer decides whether it is necessary to reallocate the power supply in the area or dispatch more resources based on the data analysis of the bottom layer.

[0014] As a preferred solution of the coal mine intelligent comprehensive management and control system based on the industrial Internet described in the present invention, the middle-level control layer receives the data of the bottom-level perception layer, and dynamically adjusts the regional power supply according to the actual load demand of each power supply area and the feedback data of the edge node, including dynamic load monitoring, real-time power supply adjustment and energy efficiency optimization; the optimization adjustment of the middle-level control layer is expressed as:

[0015] P adj，i =P i α i

[0016] Among them, P adj，i is the adjusted power supply in the ith region; P i is the original power supply of the ith region; α i is the load distribution of the ith region; and α i is a dynamic coefficient, which is dynamically adjusted through the data transmitted by the underlying perception layer, and is expressed as:

[0017] α i =f(L i , S i , E i )

[0018] Among them, L i represents the real-time load demand in the current area, S i Represents the overall status of the equipment in the area, E i represents the energy efficiency index of the equipment in this area; further, f(L i , S i , E i ) is adjusted according to the real-time parameters. In the real-time power supply adjustment, the incremental adjustment formula is expressed as:

[0019] α i (t+1)=α i (t)+Δα i

[0020] Among them, Δα i is an adjustment increment and t represents the current time step.

[0021] As a preferred solution of the coal mine intelligent comprehensive management and control system based on the industrial Internet described in the present invention, the middle-level control layer receives the fault information of the bottom-level perception layer and immediately executes the fault handling mechanism; if it is a device failure, the middle-level control layer enables the backup or redundant equipment to avoid power supply interruption, which is expressed as:

[0022]

[0023] Among them, P red，i is the amount of redundant power supply enabled after a failure; Rk Indicates the power supply capacity of standby device k; δ k is the indicator function. If device k is enabled, then δ k =1, otherwise 0; if a device is detected to have a serious fault and cannot be processed through redundancy, the middle control layer will immediately take isolation measures to disconnect the faulty device from the power grid to prevent it from affecting the entire system; and transmit the control analysis to the top management layer to optimize global resources and issue control instructions.

[0024] As a preferred solution of the coal mine intelligent comprehensive management and control system based on the industrial Internet described in the present invention, the top-level management layer constructs an energy demand prediction model by comprehensively analyzing historical data, real-time collected data and environmental data, and uses a machine learning algorithm to accurately estimate future energy demand, which is expressed as:

[0025] D total (t) = f(D hist , D real (t), E)

[0026] Among them, D total (t) represents the total energy demand forecast value at the future time t; D hist Represents historical energy consumption data; D real (t) represents the energy consumption data collected in real time at the current time t; E represents environmental data; the random forest algorithm is used to calculate the energy consumption data based on historical data D hist Train multiple decision trees, each built on a different random sample, and independently predict future energy demand; real (t) and environmental data E are input into these decision trees, and the final prediction result D is obtained through the integration method. total (t), the prediction formula is expressed as:

[0027]

[0028] Where M is the number of decision trees; T m is the prediction result of energy demand by the mth decision tree.

[0029] As a preferred solution of the coal mine intelligent comprehensive management and control system based on industrial Internet described in the present invention, global resource optimization is performed based on the prediction results to ensure the maximum energy supply efficiency and reduce the loss in energy transmission. The optimization problem is expressed as:

[0030]

[0031] Among them, P i is the power supply of the ith area; C iis the energy cost of the ith region, including electricity price and equipment operation cost; P loss，i represents the power transmission loss of the ith area, and n represents the total number of areas.

[0032] As a preferred solution of the coal mine intelligent comprehensive management and control system based on the industrial Internet described in the present invention, based on the regulation and control analysis of the middle control layer, if the energy demand of a certain area exceeds the currently available power supply and cross-regional resource allocation is required, the power supply plan of the area and the adjacent areas is dynamically adjusted to redistribute the load to reduce the power supply pressure in the fault area, which is expressed as:

[0033]

[0034] Among them, γ ij is the adjustment factor, which determines how much power is adjusted from the adjacent area j to relieve the load pressure of area i, effectively avoiding equipment overload or damage, while ensuring the balance of power supply in adjacent areas

[0035] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned industrial Internet-based coal mine intelligent comprehensive management and control system.

[0036] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the above-mentioned industrial Internet-based coal mine intelligent comprehensive management and control system is implemented.

[0037] The beneficial effect of the present invention is that the present invention reasonably arranges edge computing nodes and uses them to make local intelligent decisions and dynamic resource allocation, which greatly improves the real-time response capability and computing efficiency of the system. And through the collaborative work of the top, middle and bottom layers, the global optimization and local dynamic allocation of the coal mine power supply system are realized to avoid energy waste and power supply imbalance. The intelligent power management of the real-time feedback mechanism and cross-regional allocation strategy ensures the reliability and stability of the system when the load fluctuates. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0039] Figure 1 This is a flow chart of the intelligent comprehensive management and control system for coal mines based on the Industrial Internet. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0042] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0043] Example 1

[0044] Reference Figure 1 , which is the first embodiment of the present invention, and provides an intelligent comprehensive management and control system for coal mines based on the industrial Internet, including:

[0045] The top management layer, the middle control layer and the bottom perception layer.

[0046] The bottom perception layer is responsible for collecting power parameters, monitoring equipment status, executing control instructions, and uploading real-time operation data to the middle control layer.

[0047] The middle control layer receives the data from the bottom perception layer and is a regional energy control node. It is responsible for executing local power supply optimization, load balancing management and fault warning processing, and summarizes and transmits regional status information to the top management layer.

[0048] The top-level management layer receives the summary information, formulates global strategies, monitors system status, and allocates cross-regional resources, and sends the global strategies to the middle-level control layer to execute a new round of management and control.

[0049] Through the intelligent layout of edge computing nodes, coordinated control of each layer is achieved to complete power supply optimization, load balancing and fault warning in various areas of the coal mine, including:

[0050] Edge nodes are deployed near important power equipment to ensure real-time collection of power parameters and environmental data of key equipment for local intelligent analysis. Important power equipment deployment includes:

[0051] High-voltage substation deployment is responsible for voltage rise and fall, switching and dispatching. The deployment of edge nodes should be able to monitor key parameters such as power flow, real-time voltage, current, power factor, etc. At the same time, edge nodes can also monitor the operating status of equipment, such as transformer temperature, winding insulation status, etc. Through local analysis and early warning mechanisms, when power equipment is abnormal, it can respond immediately locally to reduce the time of failure.

[0052] At the same time, edge computing nodes are deployed near the generator sets to realize real-time monitoring of the generator's output power, speed, and unit status, and combine local intelligent algorithms to predict its operating status and provide fault warnings.

[0053] S1. The bottom perception layer is responsible for collecting power parameters, monitoring equipment status, executing control instructions, and uploading real-time operation data to the middle control layer.

[0054] The underlying perception layer collects the operating status and power parameters of the equipment in real time through sensors, including voltage, current and power factor for monitoring power supply conditions; temperature, vibration and speed for judging the health status and operating efficiency of the equipment. These data are then transmitted to the edge computing node for local processing and analysis.

[0055] The local edge computing node classifies the sensor data into “normal operation” or “fault state” based on the detection algorithm of support vector machine (SVM).

[0056] Specifically, the classification decision function of SVM is expressed as:

[0057] f(x)=w T x+b

[0058] Among them, x = [I, V, P, T, X] is a feature vector, which represents the sensor data at the current moment, I represents current, V represents voltage, P represents power, which represents the energy rate delivered by the power system to the device, T represents temperature, X represents vibration, which represents the movement frequency or amplitude of the mechanical parts of the device, and w is a weight vector, which represents the contribution of each feature to the decision. b is a bias term, which is used to adjust the position of the decision boundary. f(x) is the output of the decision function, which is used to determine which category the sample belongs to.

[0059] Based on the binary problem, if f(x)>0, it is judged as a "normal state", and if f(x)<0, it is judged as a "fault state".

[0060] Before making a decision, the SVM model needs to be trained. By adjusting the weight w and bias b, the number of samples with classification errors can be minimized, which can be expressed as:

[0061]

[0062] Among them, ||w|| 2 is the weight regularization term, which is used to control the complexity of the model and avoid overfitting. C is the penalty parameter, which controls the tolerance of the model to misclassified samples. i It is a slack variable used to deal with the situation where the data cannot be linearly separated. It represents the classification error of sample i, and n is the number of samples.

[0063] The weight vector w and bias b are obtained through optimization, thereby determining the classification decision function f(x).

[0064] The local edge node computing data is processed based on the trained SVM model. If it is determined to be a "fault state", an alarm is triggered, the operator is notified, and the fault information is uploaded to the middle control layer so that the management can respond quickly to the overall operating status of the system.

[0065] In the event of a serious fault, including a short circuit or device failure, the underlying sensing layer automatically triggers the fault isolation mechanism. The isolation mechanism involves disconnecting the power supply to the faulty area to avoid affecting the normal operation of other areas.

[0066] The fault detection results of the bottom perception layer will be immediately uploaded to the middle control layer for decision making.

[0067] The middle control layer analyzes the data from the bottom layer and decides whether it is necessary to reallocate power supply within the area or dispatch more resources.

[0068] S2. The middle control layer receives the data from the bottom perception layer and is a regional energy control node. It is responsible for executing local power supply optimization, load balancing management and fault warning processing, and summarizes and transmits regional status information to the top management layer.

[0069] The middle control layer dynamically adjusts the regional power supply according to the actual load demand of each power supply area and the feedback data of the edge nodes to ensure the stability and efficiency of power supply. This includes dynamic load monitoring, real-time power supply adjustment and energy efficiency optimization.

[0070] The optimization adjustment of the middle control layer is expressed as:

[0071] P adj，i =P i α i

[0072] Among them, P adj，i is the adjusted power supply in the ith region; P iis the original power supply of the ith region; α i is the load sharing factor for the ith region.

[0073] α i It is a dynamic factor used to adjust the power supply according to the real-time load. It takes into account multiple factors, including the energy efficiency of the equipment in the area, the actual load changes, the equipment operating status, and the changes in the power supply demand in other areas.

[0074] Then α i The calculation is dynamically adjusted through the data transmitted by the underlying perception layer, including the load data L i Represents the real-time load demand in the current area; equipment status S i Represents the overall status of key equipment in the area. It is a comprehensive indicator, including the health status and operating efficiency of the equipment. i Indicates the energy efficiency index of the equipment in this area.

[0075] Then α i It is expressed as:

[0076] α i =f(L i , S i , E i )

[0077] Furthermore, f(L i , S i , E i ) is a model that is adjusted according to real-time parameters. In real-time power supply adjustment, the incremental adjustment formula is expressed as:

[0078] α i (t+1)=α i (t)+Δα i

[0079] Among them, Δα i is an adjustment increment, calculated based on load changes and equipment status to ensure a smooth power supply adjustment process and avoid drastic fluctuations. t represents the current time step, and α i (t) represents the load distribution factor of the i-th region at time t, α i (t+1) represents the load distribution factor of the i-th area at the next time t+1, that is, the adjusted distribution factor.

[0080] In order to achieve load balancing, the power supply balance between adjacent areas is considered. When the load in a certain area increases, the middle control layer temporarily dispatches the power supply resources of the adjacent areas to ensure the smooth operation of the power supply network as a whole, and uses a proportional integral controller to perform load balancing calculations, which can be expressed as:

[0081]

[0082] in, is the reference load value of region i, L i is the actual load value, K p and K i is the controller parameter. Through mutual adjustment, the middle control layer can dynamically balance the power supply demand of each area and ensure the effect of local load optimization.

[0083] Furthermore, when the middle control layer receives the fault information from the bottom perception layer, it immediately executes the fault handling mechanism, including:

[0084] If there is a device failure, the middle control layer will enable backup or redundant equipment to avoid power outages, as shown in the following:

[0085]

[0086] Among them, P red，i is the amount of redundant power supply enabled after a failure; R k Indicates the power supply capacity of standby device k; δ k is the indicator function. If device k is enabled, then δ k =1, otherwise 0.

[0087] If a serious fault is detected in a device and cannot be handled through redundancy, the middle control layer will immediately take isolation measures to disconnect the faulty device from the power grid to prevent it from affecting the entire system.

[0088] The control analysis is transmitted to the top management level for global resource optimization, and then transmitted to the middle control level again, which issues control instructions.

[0089] S3. The top-level management layer receives the summary information, formulates global strategies, monitors system status, and allocates cross-regional resources, and sends the global strategies to the middle-level control layer to execute a new round of management and control.

[0090] The top management constructs an energy demand forecasting model by conducting a comprehensive analysis of historical data, real-time collected data, and environmental data, and uses machine learning algorithms to accurately estimate future energy demand.

[0091] Specifically, the prediction model calculates the total energy demand D at the future time t through the function f total (t), expressed as:

[0092] D total (t) = f(D hist , D real (t), E)

[0093] Among them, D total(t) represents the total energy demand forecast value at the future time t; D hist Represents historical energy consumption data; D real (t) represents the energy consumption data collected in real time at the current time t; E represents environmental data.

[0094] Based on the historical data D hist Multiple decision trees are trained, each built on a different random sample, and independently predict future energy demand.

[0095] The real-time data real (t) and environmental data E are input into these decision trees, and the final prediction result D is obtained through the integration method. total (t), the prediction formula is expressed as:

[0096]

[0097] Where M is the number of decision trees; T m is the prediction result of energy demand by the mth decision tree.

[0098] By combining historical data, real-time data and environmental factors, the random forest model can provide more accurate forecasts of future energy demand.

[0099] Based on the predicted energy demand, global resource optimization is performed to ensure that the energy supply efficiency is maximized while reducing the loss in energy transmission. The optimization problem is expressed as:

[0100]

[0101] Among them, P i is the power supply of the ith area; C i is the energy cost of the ith region, including electricity price and equipment operation cost; P loss，i represents the power transmission loss of the ith area, and n represents the total number of areas.

[0102] According to the regulation and analysis of the middle control layer, if the energy demand of a certain area exceeds the current available power supply, cross-regional resource allocation is required. In this case, the power supply plan of the area and the adjacent areas is dynamically adjusted to redistribute the load to reduce the power supply pressure in the fault area, which is expressed as:

[0103]

[0104] Among them, γ ij is the adjustment factor, which determines how much power is adjusted from the adjacent area j to relieve the load pressure of area i. By redistributing the load in real time, it is possible to effectively avoid equipment overload or damage while ensuring the balance of power supply in adjacent areas.

[0105] Furthermore, the top-level management layer sends the global strategy to the middle control layer. The middle control layer performs local optimization and fault warning based on the actual situation in the area, and sends the control instructions to the bottom perception layer. The bottom perception layer executes the control instructions sent by the upper layer by monitoring the status data of the equipment and combining it with the local analysis of the edge nodes to achieve global optimization and local dynamic allocation of the coal mine power supply system, thereby avoiding energy waste and power supply imbalance.

[0106] In summary, the present invention has greatly improved the real-time response capability and computing efficiency of the system by rationally laying out edge computing nodes and using them for local intelligent decision-making and dynamic resource allocation. And through the collaborative work of the top, middle and bottom layers, the global optimization and local dynamic allocation of the coal mine power supply system are realized to avoid energy waste and power supply imbalance. Intelligent power management with real-time feedback mechanism and cross-regional allocation strategy ensures the reliability and stability of the system when the load fluctuates.

[0107] Example 2

[0108] On the basis of the first embodiment, in order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments, including:

[0109] Take a coal mine as an example. The mining area is 5 square kilometers and has 10 main power supply areas, including coal mining face, tunneling face, main transportation lane, auxiliary transportation lane, ventilation room, drainage pump room and other key power supply areas. The specific implementation process of the system is as follows:

[0110] A total of 15 edge computing nodes are deployed in 10 power supply areas, including:

[0111] Coal mining face: 3 nodes;

[0112] Excavation working face: 2 nodes;

[0113] Main transport lanes: 2 nodes;

[0114] Auxiliary transport lane: 2 nodes;

[0115] Ventilation room: 2 nodes;

[0116] Drainage pump room: 2 nodes;

[0117] Other regions: 2 nodes.

[0118] The data sampling period is set to 100ms and the update period is set to 1s. The experimental results are shown in Table 1:

[0119] Table 1 Comparison of edge node deployment effects

[0120]

[0121]

[0122] The statistics of load prediction accuracy at future moments are shown in Table 2:

[0123] Table 2 Load prediction accuracy statistics

[0124] Forecast period Predicted value (kW) Actual value (kW) Error rate (%) t+1h 185 182 1.65 t+2h 190 188 1.06 t+3h 176 175 1.71 t+4h 171 169 1.18

[0125] From Table 1 and Table 2, we can find that the delay optimization effect is closely related to the load characteristics of the power supply area. The delay improvement rate in the high-load area (coal mining and tunneling working face) is the most significant, exceeding 62%. The delay after optimization in each area is controlled within 320ms, meeting the real-time control requirements. The optimization effect shows obvious stratification characteristics, giving priority to ensuring the power supply quality of key production areas such as mining working faces.

[0126] It performs outstandingly in short-term load forecasting, with the forecast error rate of 1 to 4 hours always kept within 2%, among which the forecast of 2 hours is the most accurate, with an error rate of only 1.06%. The stability and reliability of the forecast accuracy provide strong support for the system to carry out forward-looking control, and effectively meet the requirements of industrial sites for forecast accuracy.

[0127] This embodiment also provides a computer device, which is suitable for the situation of an intelligent comprehensive management and control system for coal mines based on the industrial Internet, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to realize the intelligent comprehensive management and control system for coal mines based on the industrial Internet as proposed in the above embodiment.

[0128] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFc (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, a trackball or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0129] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, an intelligent comprehensive management and control system for coal mines based on the industrial Internet is implemented as proposed in the above embodiment.

[0130] The storage medium proposed in this embodiment and the data storage system proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent comprehensive management and control system for coal mines based on the industrial Internet, characterized by: include: The top management layer, the middle control layer, and the bottom perception layer; The bottom perception layer is responsible for collecting power parameters, monitoring equipment status, executing control instructions, and uploading real-time operation data to the middle control layer; The middle control layer receives the data from the bottom perception layer and is a regional energy control node responsible for executing local power supply optimization, load balancing management and fault warning processing, and summarizing and transmitting regional status information to the top management layer; The top-level management layer receives summary information, formulates global strategies, monitors system status, and allocates cross-regional resources, and sends global strategies to the middle-level control layer to execute a new round of management and control.

2. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 1 is characterized by: The underlying perception layer collects the operating status and power parameters of the equipment in real time through sensors, including voltage, current, power factor, temperature, vibration, and speed, and transmits the data to the edge computing node for local processing and analysis; The local processing adopts the detection model of support vector machine SVM, and the classification decision function of the detection model is expressed as: f(x)=w T x+b Among them, x = [I, V, P, T, X] is a feature vector representing the sensor data at the current moment, I represents current, V represents voltage, P represents power, T represents temperature, X represents vibration, w is the weight vector, b is the bias term, and f(x) is the output of the decision function.

3. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 2 is characterized by: The SVM model is trained to minimize the number of misclassified samples by adjusting the weight w and bias b, which is expressed as: Among them, ||w||2 is the regularization term of the weight, c is the penalty parameter, which controls the tolerance of the model to misclassified samples, and ξ i is a slack variable, representing the classification error of sample i, and n is the number of samples; The local edge node computing data is processed based on the trained SVM model. If it is determined to be a "fault state", an alarm is triggered to notify the operator, and the fault information is uploaded to the middle control layer. The middle control layer decides whether it is necessary to reallocate the power supply in the area or dispatch more resources based on the underlying data analysis.

4. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 3 is characterized by: The middle control layer receives the data from the bottom perception layer and dynamically adjusts the regional power supply according to the actual load demand of each power supply area and the feedback data of the edge nodes, including dynamic load monitoring, real-time power supply adjustment and energy efficiency optimization; The optimization adjustment of the middle control layer is expressed as: P adj，i =P i ·α i Among them, P adj，i is the adjusted power supply in the ith region; P i is the original power supply of the ith region; α i is the load distribution of the ith region; and α i is a dynamic coefficient, which is dynamically adjusted through the data transmitted by the underlying perception layer, expressed as: a i =f(L i ,S i ,E i ) Among them, L i represents the real-time load demand in the current area, S i Represents the overall status of the equipment in the area, E i Indicates the energy efficiency index of the equipment in this area; Furthermore, f(L i , S i , E i ) is adjusted according to the real-time parameters. In the real-time power supply adjustment, the incremental adjustment formula is expressed as: a i (t+1)=a i (t)+Da i Among them, Δα i is an adjustment increment and t represents the current time step.

5. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 4 is characterized by: The middle control layer receives the fault information from the bottom perception layer and immediately executes the fault handling mechanism; If there is a device failure, the middle control layer activates the backup or redundant equipment to avoid power interruption, which is expressed as: Among them, P red，i is the amount of redundant power supply enabled after a failure; R k Indicates the power supply capacity of standby device k; δ k is the indicator function. If device k is enabled, then δ k =1, otherwise 0; If a device is detected to have a serious fault and cannot be handled through redundancy, the middle control layer will immediately take isolation measures to disconnect the faulty device from the power grid to prevent it from affecting the entire system; The control analysis will be transmitted to the top management level to optimize global resources and issue control instructions.

6. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 5 is characterized by: The top management layer constructs an energy demand forecasting model by comprehensively analyzing historical data, real-time collected data, and environmental data, and uses machine learning algorithms to accurately estimate future energy demand, which is expressed as: D total (t)=f(D hist ,D real (t),E) Among them, D total (t) represents the total energy demand forecast value at the future time t; D hist Represents historical energy consumption data; D real (t) represents the energy consumption data collected in real time at the current time t; E represents environmental data; Based on the historical data D hist Train multiple decision trees, each built on a different random sample, and independently predict future energy demand; The real-time data real (t) and environmental data E are input into these decision trees, and the final prediction result D is obtained through the integration method. total (t), the prediction formula is expressed as: Where M is the number of decision trees; T m is the prediction result of energy demand by the mth decision tree.

7. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 6 is characterized by: Based on the prediction results, global resource optimization is performed to ensure that energy supply efficiency is maximized while reducing energy transmission losses. The optimization problem is expressed as: Among them, P i is the power supply of the ith area; C i is the energy cost of the ith region, including electricity price and equipment operation cost; P loss，i represents the power transmission loss of the ith area, and n represents the total number of areas.

8. The coal mine intelligent comprehensive management and control system based on the industrial Internet as claimed in claim 7, characterized in that: Based on the regulatory analysis of the middle control layer, If the energy demand in a certain area exceeds the currently available power supply and cross-regional resource allocation is required, the top-level management layer dynamically adjusts the power supply plan of the area and adjacent areas to redistribute the load to reduce the power supply pressure in the faulty area, which is expressed as: Among them, γ ij is the adjustment factor, which determines how much power supply is adjusted from the adjacent area j to relieve the load pressure of area i, effectively avoiding equipment overload or damage, while ensuring the balance of power supply in adjacent areas.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the industrial Internet-based coal mine intelligent comprehensive management and control system described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the industrial Internet-based coal mine intelligent comprehensive management and control system described in any one of claims 1 to 8 are implemented.

Images