A mine explosion-proof frequency converter energy-saving optimization system

Abstract

The present application relates to the technical field of frequency converter energy saving, and particularly relates to a mine-used explosion-proof frequency converter energy saving optimization system, which specifically comprises: an upper computer, a switch, a PID controller, a power distribution cabinet, a frequency converter, a driving motor, a belt conveyor, a laser radar sensor, a speed sensor and an intelligent frequency conversion module; the present application aims at the problem that the traditional coal flow measurement method of the transport scale causes a delay between measurement and control, uses the laser radar sensor to measure the coal flow on the belt conveyor in an integral method, eliminates the hysteresis effect and improves the measurement accuracy; aiming at the problem that the traditional PID control strategy has low control accuracy, the intelligent frequency conversion module is proposed, and the energy saving optimization model based on the BP neural network and the PID control model based on the fuzzy neural network are used in the intelligent frequency conversion module to realize the frequency conversion control of the belt conveyor, so that the belt conveyor can maintain high energy saving efficiency and high reliability.

Description

Technical Field

[0001] This invention relates to the field of frequency converter energy-saving technology, specifically to an energy-saving optimization system for a mine explosion-proof frequency converter. Background Technology

[0002] With the rapid development of the coal mining industry, the energy consumption problem of mining electrical equipment has become increasingly prominent. Explosion-proof frequency converters play a crucial role in coal mine production. Therefore, in order to improve the operating efficiency of mining electrical equipment, reduce energy consumption, and ensure coal mine production safety, this invention proposes an energy-saving optimization system for explosion-proof frequency converters used in mines. This system is mainly applied to the energy-saving optimization frequency conversion of underground belt conveyors in coal mines. However, existing energy-saving optimization systems for explosion-proof frequency converters used in mines have the following problems:

[0003] (1) The traditional method of measuring coal flow using a transport scale results in a time delay between measurement and control, making the frequency converter control response insufficient;

[0004] (2) When using the traditional PID control strategy, the control accuracy is not high under the nonlinear operation of the belt conveyor. Summary of the Invention

[0005] To address the above issues and overcome the shortcomings of existing technologies, this invention provides an energy-saving optimization system for explosion-proof frequency converters used in mines. Addressing the problem of time delays between measurement and control caused by traditional methods of measuring coal flow using conveyor scales, resulting in untimely frequency converter control response, this invention utilizes a lidar sensor to obtain laser point cloud data of coal on the belt conveyor. Noise reduction is achieved through a K-means clustering algorithm combined with an adaptive threshold filtering algorithm. The coal flow is then calculated using an integral method, providing data support for frequency converter regulation. This eliminates the hysteresis effect in traditional measurement methods while improving measurement accuracy, ensuring the accuracy and stability of frequency converter regulation for underground coal mine belt conveyors. Furthermore, it addresses the issue of low control accuracy when using traditional PID control strategies under nonlinear operation conditions of belt conveyors. To address this problem, this invention proposes an intelligent frequency conversion module. Within this module, an energy-saving optimization model based on a BP neural network and a PID control model based on a fuzzy neural network are used to achieve automatic energy-saving frequency conversion control of the belt conveyor. The BP neural network-based energy-saving optimization model learns the relationship between coal flow rate, conveyor belt speed, and belt conveyor power, obtaining the optimal operating speed of the belt conveyor under a fixed coal flow rate. Simultaneously, the fuzzy neural network-based PID control model further optimizes the control strategy, and the kinetic energy coefficient is used to correct the center value and width of the Gaussian membership function. This avoids the problems of low control accuracy and over-adjustment in traditional control strategies, enabling the belt conveyor to maintain high energy efficiency and high reliability even when dealing with complex operating conditions such as nonlinear and time-varying loads.

[0006] The technical solution adopted by the present invention is as follows: The present invention provides an energy-saving optimization system for explosion-proof frequency converters in mines, specifically including: a host computer, a switch, a PID controller, a power distribution cabinet, a frequency converter, a drive motor, a belt conveyor, a lidar sensor, a speed sensor, and an intelligent frequency conversion module;

[0007] The host computer communicates and exchanges data with the PID controller through a switch;

[0008] The switch receives signals from the host computer and forwards them to the PID controller;

[0009] The PID controller sends a frequency control signal to the frequency converter;

[0010] The aforementioned power distribution cabinet provides power to the frequency converter;

[0011] The frequency converter receives control signals from the PID controller and adjusts the frequency to change the speed of the drive motor;

[0012] The drive motor is speed-controlled by a frequency converter, which drives the belt conveyor to operate;

[0013] The belt conveyor described above uses a conveyor belt to transport coal mined underground in a coal mine;

[0014] The aforementioned lidar sensor is fixed above the belt conveyor to obtain laser point cloud data of the coal on the belt conveyor;

[0015] The speed sensor is installed on the belt conveyor to obtain the actual running speed of the conveyor belt;

[0016] The intelligent frequency conversion module calculates the coal flow rate based on the laser point cloud data of the coal, and uses an energy-saving optimization model based on BP neural network and a PID control model based on fuzzy neural network to realize automatic energy-saving frequency conversion control of the belt conveyor.

[0017] The intelligent frequency conversion module specifically includes a coal flow calculation unit, an energy-saving optimization unit, and a fuzzy control unit, which are connected in a unidirectional manner in sequence.

[0018] The coal flow calculation unit calculates the coal flow rate using a lidar sensor, and the specific steps are as follows:

[0019] Step S1: Obtain laser point cloud data: The laser pulse is emitted to the belt conveyor through the lidar sensor to obtain the laser point cloud data of the coal. The laser point cloud data specifically includes the rotation angle of each laser point and the distance of each laser point from the lidar sensor.

[0020] Step S2: Establish a Cartesian coordinate system: with the position of the lidar sensor as the origin, the direction of the conveyor belt as the Z-axis, the scanning direction with a rotation angle of 0 degrees for the laser pulse perpendicular to the Z-axis as the X-axis, and the direction perpendicular to both the X-axis and the Z-axis as the Y-axis.

[0021] Step S3: Construct the coal cross-section diagram: The plane containing the origin, the X-axis, and the Y-axis is taken as the OXY plane. The coal cross-section diagram is composed of the laser point cloud data of the coal in the OXY plane.

[0022] Step S4: Denoise the laser point cloud data using the K-means clustering algorithm combined with an adaptive threshold filtering algorithm;

[0023] Step S5: Calculate the area of ​​the coal cross-section;

[0024] Step S6: Calculate the coal flow rate. The specific formula is as follows:

[0025]

[0026] Where Q is the coal flow rate and ρ is the average density of the coal, in kg / m³. 3 p is the frame rate of the lidar sensor, in FPS; M is the total number of coal cross-section images; v is the conveyor belt speed, in m / s; S total (j) represents the area of ​​the j-th coal cross-section, in m². 2 .

[0027] Furthermore, the specific steps for denoising the laser point cloud data using the K-means clustering algorithm combined with the adaptive threshold filtering algorithm in step S4 are as follows:

[0028] Step S41: Cluster the laser point cloud data using the K-means clustering algorithm;

[0029] Step S42: Calculate the local density of each laser point in the cluster using the Gaussian kernel function. The specific calculation formula is as follows:

[0030]

[0031] Where, ρ x Let x represent the local density of laser point x, U represent any cluster, x and x' represent any laser point in U, dis(x,x') represent the Euclidean distance between x and x', and h represent the width parameter of the Gaussian kernel function.

[0032] Step S43: Calculate the standard deviation of the local density of all laser points in the cluster, and use three times the standard deviation as the adaptive threshold of the cluster;

[0033] Step S44: Remove laser points in each cluster whose local density is outside the adaptive threshold of that cluster.

[0034] Furthermore, the specific steps for calculating the area of ​​the coal cross-section diagram in step S5 are as follows:

[0035] Step S51: Record two adjacent laser pulses in the laser pulses emitted by the lidar sensor in the OXY plane that detect coal as the first pulse and the second pulse, wherein the rotation angle of the first pulse is larger than the rotation angle of the second pulse;

[0036] Step S52: Denote the two adjacent laser points generated at the bottom of the coal cross-section diagram by the first and second pulses as points A and B, respectively, and denote the rotation angles of points A and B as θ. A and θ B ;

[0037] Step S53: The two adjacent laser points generated by the first pulse and the second pulse at the top of the coal cross-section diagram are respectively recorded as point C and point D. The rotation angle of point C is the same as that of point A, and the rotation angle of point D is the same as that of point B.

[0038] Step S54: Calculate the area of ​​the quadrilateral formed by points A, B, C, and D. The specific formula is as follows:

[0039]

[0040] Among them, S ABCD This represents the area of ​​the quadrilateral formed by points A, B, C, and D, expressed in meters (m²). 2 S ΔOAB Let S represent the area of ​​the triangle formed by the origin, point A, and point B. ΔOCD L represents the area of ​​the triangle formed by the origin, point C, and point D. A L B L C and L D These represent the distances from points A, B, C, and D to the lidar sensor, respectively, in meters (m).

[0041] Step S55: View the coal cross-section diagram as a figure composed of several quadrilaterals. The specific formula for calculating the area of ​​the coal cross-section diagram is as follows:

[0042]

[0043] Among them, S total This represents the area of ​​a coal cross-section, in meters (m²). 2 N represents the total number of laser pulses emitted by the lidar sensor in the OXY plane that detected coal, i is the index of the laser pulse, and θ i+1 and θi L represents the rotation angles of the (i+1)th and ith laser pulses, respectively, in degrees. i+1 L i L' represents the distance from the laser point generated at the bottom of the coal cross-section diagram by the (i+1)th and ithth laser pulses to the lidar sensor, respectively, in meters. i+1 and L' i These represent the distances from the laser points generated at the top of the coal cross-section diagram by the (i+1)th and ith laser pulses to the lidar sensor, respectively, in meters.

[0044] The energy-saving optimization unit constructs an energy-saving optimization model based on a BP neural network, learns the relationship between coal flow rate, conveyor belt speed and belt conveyor power, and obtains the optimal speed under the condition of fixed coal flow rate. The optimal speed is the conveyor belt speed when the power of the belt conveyor is minimized. The energy-saving optimization model based on the BP neural network specifically includes a BP input layer, a hidden layer and a BP output layer.

[0045] The BP input layer uses coal flow rate and conveyor belt speed as input data;

[0046] The hidden layer learns from the input data and uses the Sigmoid activation function;

[0047] The BP output layer learns from the output data of the hidden layer and obtains the power of the belt conveyor through a linear activation function.

[0048] The fuzzy control unit utilizes a PID control model based on a fuzzy neural network to achieve real-time, automatic, and precise control of the frequency signal of the frequency converter. The specific steps are as follows:

[0049] Step D1: Obtain the current operating speed of the conveyor belt through the speed sensor, and calculate the current coal flow rate through the coal flow calculation unit;

[0050] Step D2: Obtain the optimal velocity corresponding to the current coal flow rate through the energy-saving optimization unit;

[0051] Step D3: The difference between the optimal speed and the current operating speed, and the rate of change of the difference, are used as inputs. The PID control parameters are obtained by calculating the difference using a PID control model based on a fuzzy neural network. The frequency converter is then controlled using the PID control parameters.

[0052] The PID control model based on fuzzy neural networks specifically includes: a fuzzy input layer, a fuzzification layer, a fuzzy rule layer, a normalization layer, and a fuzzy output layer;

[0053] The fuzzy input layer receives input quantities, which include the difference and the rate of change of the difference.

[0054] The aforementioned fuzzification layer constructs seven fuzzy subsets, and each fuzzy subset is fuzzified using a Gaussian membership function;

[0055] The fuzzy rule layer consists of 49 nodes, each node representing a control rule;

[0056] The normalization layer normalizes the output of each node in the fuzzy rule layer;

[0057] The fuzzy output layer outputs PID control parameters;

[0058] The PID control model based on fuzzy neural network sets a first kinetic energy coefficient and a second kinetic energy coefficient to correct the center value and width of the Gaussian membership function. The specific formula is as follows:

[0059]

[0060] in, and Let α represent the center values ​​of the Gaussian membership functions of the nth fuzzy subset of the mth input in the t-th, t-1, and t-2 iterations, respectively. Let α represent the first kinetic coefficient, β represent the second kinetic coefficient, and Loss represent the loss value. mn The center value of the Gaussian membership function of the nth fuzzy subset of the mth input is represented. and σ represents the width of the Gaussian membership function of the nth fuzzy subset of the mth input in the t-th, t-1, and t-2 iterations, respectively. mn The width of the Gaussian membership function of the nth fuzzy subset of the mth input is represented.

[0061] The beneficial results achieved by the present invention using the above solution are as follows:

[0062] (1) To address the problem that the traditional method of measuring coal flow using a transport scale results in a time delay between measurement and control, which makes the frequency conversion control response not timely enough, this invention uses a lidar sensor to obtain the laser point cloud data of coal on the belt conveyor, and performs noise reduction processing on it using a K-means clustering algorithm combined with an adaptive threshold filtering algorithm. Then, the coal flow is calculated in an integral manner, providing data support for frequency conversion regulation. This eliminates the hysteresis effect in the traditional measurement method while improving the measurement accuracy, ensuring the accuracy and stability of frequency conversion regulation of belt conveyors in coal mines.

[0063] (2) To address the problem of low control accuracy in the nonlinear operation of belt conveyors when using traditional PID control strategies, this invention proposes an intelligent frequency conversion module. In the intelligent frequency conversion module, an energy-saving optimization model based on BP neural network and a PID control model based on fuzzy neural network are used to realize automatic energy-saving frequency conversion control of belt conveyors. The energy-saving optimization model based on BP neural network learns the relationship between coal flow, conveyor belt speed and belt conveyor power to obtain the optimal operating speed of belt conveyor under fixed coal flow. At the same time, the control strategy is further optimized using the PID control model based on fuzzy neural network, and the center value and width of the Gaussian membership function are corrected using the kinetic energy coefficient. This avoids the problems of low control accuracy and over-adjustment in traditional control strategies, so that belt conveyors can still maintain high energy efficiency and high reliability when dealing with complex working conditions such as nonlinear and time-varying loads. Attached Figure Description

[0064] Figure 1 This is an architecture diagram of an energy-saving optimization system for an explosion-proof frequency converter used in mining, as proposed in this invention.

[0065] Figure 2 A schematic diagram for constructing a coal cross-section diagram;

[0066] Figure 3 An auxiliary diagram for calculating the area of ​​a coal cross-section;

[0067] Figure 4 This is an architecture diagram of an energy-saving optimization model based on a BP neural network.

[0068] Figure 5 This is an architecture diagram of a PID control model based on a fuzzy neural network.

[0069] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0070] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0071] Example 1, see Figure 1 , Figure 1This is an architectural diagram of an energy-saving optimization system for a mine explosion-proof frequency converter proposed in this invention. In this embodiment, an energy-saving optimization system for a mine explosion-proof frequency converter is proposed, the specific details of which are as follows:

[0072] This invention provides an energy-saving optimization system for explosion-proof frequency converters used in mining, specifically including: a host computer, a switch, a PID controller, a power distribution cabinet, a frequency converter, a drive motor, a belt conveyor, a lidar sensor, a speed sensor, and an intelligent frequency conversion module;

[0073] The host computer communicates and exchanges data with the PID controller through a switch;

[0074] The switch receives signals from the host computer and forwards them to the PID controller.

[0075] The PID controller sends a frequency control signal to the frequency converter;

[0076] The distribution cabinet provides power to the frequency converter;

[0077] The frequency converter receives control signals from the PID controller and adjusts the frequency to change the speed of the drive motor;

[0078] The drive motor is controlled by a frequency converter to drive the belt conveyor.

[0079] Belt conveyors use conveyor belts to transport coal mined underground in coal mines;

[0080] The lidar sensor is fixed above the belt conveyor to obtain laser point cloud data of the coal on the belt conveyor;

[0081] A speed sensor is installed on the belt conveyor to obtain the actual running speed of the conveyor belt;

[0082] The intelligent frequency conversion module calculates the coal flow rate based on the laser point cloud data of the coal, and uses an energy-saving optimization model based on BP neural network and a PID control model based on fuzzy neural network to realize automatic energy-saving frequency conversion control of the belt conveyor.

[0083] The intelligent frequency conversion module specifically includes a coal flow calculation unit, an energy-saving optimization unit, and a fuzzy control unit, which are connected in a unidirectional manner in sequence.

[0084] In this embodiment, the PID controller is a Siemens S7-400; the lidar sensor is a Pepperl+Fuchs MWC25M-L2M-B16-V15 with a sensing range of 25m; and the frequency converter is a Chuang'an explosion-proof BPJ2-800 / 1140 mining explosion-proof and intrinsically safe AC frequency converter with a rated power of 800KW and a rated voltage of 1140V.

[0085] Example 2, see Figure 2 , Figure 2 To construct a schematic diagram of a coal cross-section, this embodiment, based on the above embodiment, implements a coal flow calculation unit, the specific details of which are as follows:

[0086] The coal flow calculation unit calculates the coal flow rate using a lidar sensor. The specific steps are as follows:

[0087] Step S1: Obtain laser point cloud data: The laser pulse is emitted to the belt conveyor through the lidar sensor to obtain the laser point cloud data of the coal. The laser point cloud data specifically includes the rotation angle of each laser point and the distance of each laser point from the lidar sensor.

[0088] Step S2: Establish a Cartesian coordinate system: with the position of the lidar sensor as the origin, the direction of the conveyor belt as the Z-axis, the scanning direction with a rotation angle of 0 degrees for the laser pulse perpendicular to the Z-axis as the X-axis, and the direction perpendicular to both the X-axis and the Z-axis as the Y-axis.

[0089] Step S3: Construct the coal cross-section diagram: The plane containing the origin, the X-axis, and the Y-axis is taken as the OXY plane. The coal cross-section diagram is composed of the laser point cloud data of the coal in the OXY plane.

[0090] Step S4: Denoise the laser point cloud data using the K-means clustering algorithm combined with an adaptive threshold filtering algorithm;

[0091] Step S5: Calculate the area of ​​the coal cross-section;

[0092] Step S6: Calculate the coal flow rate. The specific formula is as follows:

[0093]

[0094] Where Q is the coal flow rate and ρ is the average density of the coal, in kg / m³. 3 p is the frame rate of the lidar sensor, in FPS; M is the total number of coal cross-section images; v is the conveyor belt speed, in m / s; S total (j) represents the area of ​​the j-th coal cross-section, in m². 2 .

[0095] Example 3: Based on the above examples, this example implements noise reduction for laser point cloud data. The specific details are as follows:

[0096] The specific steps for denoising the laser point cloud data using the K-means clustering algorithm combined with the adaptive threshold filtering algorithm in step S4 are as follows:

[0097] Step S41: Cluster the laser point cloud data using the K-means clustering algorithm;

[0098] Step S42: Calculate the local density of each laser point in the cluster using the Gaussian kernel function. The specific calculation formula is as follows:

[0099]

[0100] Where, ρ x Let x represent the local density of laser point x, U represent any cluster, x and x' represent any laser point in U, dis(x,x') represent the Euclidean distance between x and x', and h represent the width parameter of the Gaussian kernel function.

[0101] Step S43: Calculate the standard deviation of the local density of all laser points in the cluster, and use three times the standard deviation as the adaptive threshold of the cluster;

[0102] Step S44: Remove laser points in each cluster whose local density is outside the adaptive threshold of that cluster.

[0103] Example 4, see Figure 3 , Figure 3 This embodiment, based on the above embodiment, implements the calculation of the area of ​​the coal cross-section as an auxiliary diagram for calculating the area of ​​the coal cross-section. The specific details are as follows:

[0104] The specific steps for calculating the area of ​​the coal cross-section in step S5 are as follows:

[0105] Step S51: Record two adjacent laser pulses in the laser pulses emitted by the lidar sensor in the OXY plane that detect coal as the first pulse and the second pulse, wherein the rotation angle of the first pulse is larger than the rotation angle of the second pulse;

[0106] Step S52: Denote the two adjacent laser points generated at the bottom of the coal cross-section diagram by the first and second pulses as points A and B, respectively, and denote the rotation angles of points A and B as θ. A and θ B The distance between A and B is Δθ;

[0107] Step S53: The two adjacent laser points generated by the first pulse and the second pulse at the top of the coal cross-section diagram are respectively recorded as point C and point D. The rotation angle of point C is the same as that of point A, and the rotation angle of point D is the same as that of point B.

[0108] Step S54: Calculate the area of ​​the quadrilateral formed by points A, B, C, and D. The specific formula is as follows:

[0109]

[0110] Among them, S ABCD This represents the area of ​​the quadrilateral formed by points A, B, C, and D, expressed in meters (m²). 2 S ΔOAB Let S represent the area of ​​the triangle formed by the origin, point A, and point B. ΔOCD L represents the area of ​​the triangle formed by the origin, point C, and point D. A L B L C and L D These represent the distances from points A, B, C, and D to the lidar sensor, respectively, in meters (m).

[0111] Step S55: View the coal cross-section diagram as a figure composed of several quadrilaterals. The specific formula for calculating the area of ​​the coal cross-section diagram is as follows:

[0112]

[0113] Among them, S total This represents the area of ​​a coal cross-section, in meters (m²). 2 N represents the total number of laser pulses emitted by the lidar sensor in the OXY plane that detected coal, i is the index of the laser pulse, and θ i+1 and θ i L represents the rotation angles of the (i+1)th and ith laser pulses, respectively, in degrees. i+1 L i L' represents the distance from the laser point generated at the bottom of the coal cross-section diagram by the (i+1)th and ithth laser pulses to the lidar sensor, respectively, in meters. i+1 and L' i These represent the distances from the laser points generated at the top of the coal cross-section diagram by the (i+1)th and ith laser pulses to the lidar sensor, respectively, in meters.

[0114] Example 5, see Figure 4 , Figure 4 The following is an architecture diagram of the energy-saving optimization model based on a BP neural network. This embodiment, based on the above embodiment, implements an energy-saving optimization unit, the specific details of which are as follows:

[0115] The energy-saving optimization unit constructs an energy-saving optimization model based on a BP neural network, learns the relationship between coal flow rate, conveyor belt speed and belt conveyor power, and obtains the optimal speed under the condition of fixed coal flow rate. The optimal speed is the conveyor belt speed when the power of the belt conveyor is minimized. The energy-saving optimization model based on the BP neural network specifically includes a BP input layer, a hidden layer and a BP output layer.

[0116] The BP input layer uses coal flow rate and conveyor belt speed as input data;

[0117] The hidden layer learns from the input data and uses the Sigmoid activation function, the specific formula of which is as follows:

[0118] Y1 = sigmoid(IW1 + B1);

[0119] Where Y1 represents the output of the hidden layer, sigmoid represents the sigmoid activation function, I represents the matrix composed of the running speed of the coal flow conveyor belt, W1 represents the weight parameters of the hidden layer, and B1 represents the bias parameters of the hidden layer.

[0120] The BP output layer learns from the output data of the hidden layer and obtains the power of the belt conveyor through a linear activation function. The specific formula is as follows:

[0121] P = Linear(Y1W2 + B2);

[0122] Where P represents the power of the belt conveyor, Linear represents the linear activation function, W2 represents the weight parameters of the BP output layer, and B2 represents the bias parameters of the BP output layer.

[0123] In this embodiment, the average coal flow rate over five minutes is calculated, and the operating speed of the conveyor belt is adjusted until the belt conveyor reaches a stable operating state. The power of the belt conveyor at this time is the optimal power of the belt conveyor under the average coal flow rate. The average coal flow rate, the operating speed of the conveyor belt, and the power of the belt conveyor at this time are recorded as a set of experimental data. This process is repeated to obtain 79 sets of experimental data, which are divided into training set and test set in an 8:2 ratio to train the energy-saving optimization model based on BP neural network.

[0124] Example 6, see Figure 5 , Figure 5 The diagram shows the architecture of the PID control model based on a fuzzy neural network. This embodiment, based on the previous embodiment, implements a fuzzy control unit, as detailed below:

[0125] The fuzzy control unit utilizes a PID control model based on a fuzzy neural network to achieve real-time, automatic, and precise control of the frequency signal of the frequency converter. The specific steps are as follows:

[0126] Step D1: Obtain the current operating speed of the conveyor belt through the speed sensor, and calculate the current coal flow rate through the coal flow calculation unit;

[0127] Step D2: Obtain the optimal velocity corresponding to the current coal flow rate through the energy-saving optimization unit;

[0128] Step D3: The difference between the optimal speed and the current operating speed, and the rate of change of the difference, are used as inputs. The PID control parameters are obtained by calculating the difference using a PID control model based on a fuzzy neural network. The frequency converter is then controlled using the PID control parameters.

[0129] The PID control model based on fuzzy neural networks specifically includes: a fuzzy input layer, a fuzzification layer, a fuzzy rule layer, a normalization layer, and a fuzzy output layer;

[0130] The fuzzy input layer receives input quantities, which include the difference and the rate of change of the difference.

[0131] The fuzzification layer constructs seven fuzzy subsets, and each fuzzy subset is fuzzified using a Gaussian membership function. The seven fuzzy subsets are NB, NM, NS, ZO, PS, PM, and PB, representing negative large, negative medium, negative small, zero, positive small, positive medium, and positive large, respectively. The specific calculation formula for the fuzzification layer is as follows:

[0132]

[0133] Where Out2(m,n) t X represents the output of the nth fuzzy subset of the m-th input in the fuzzification layer during the t-th iteration, where m represents the index of the input, m=1 represents the difference, m=2 represents the rate of change of the difference, and n represents the index of the fuzzy subset. mn This represents the output of the fuzzy input layer. This represents the center value of the Gaussian membership function of the nth fuzzy subset of the mth input in the t-th iteration. The width of the Gaussian membership function of the nth fuzzy subset of the mth input in the tth iteration is represented.

[0134] The fuzzy rule layer consists of 49 nodes, each node representing a control rule. The specific calculation formula is as follows:

[0135] Out3(k) t =Out2(1,n1) t ×Out2(2,n2) t ;

[0136] Among them, Out3(k) t Let Out2(1,n1) represent the output of the k-th node in the t-th iteration of the fuzzy rule layer. t Out2(2,n2) represents the fuzzification layer output of the n1-th fuzzy subset of the differences in the t-th iteration. t The output of the fuzzification layer for the n2th fuzzy subset represents the rate of change of the difference in the t-th iteration.

[0137] The normalization layer normalizes the output of each node in the fuzzy rule layer. The specific calculation formula is as follows:

[0138]

[0139] Among them, Out4(k) t Out3(a) represents the output of the k-th node in the normalization layer during the t-th iteration. t This represents the output of the a-th node in the fuzzy rule layer during the t-th iteration.

[0140] The fuzzy output layer outputs PID control parameters, including K. p K i K d The specific calculation formula is as follows:

[0141]

[0142] Where, ω t This represents the weight in the t-th iteration.

[0143] The formula for calculating the loss function of the PID control model based on fuzzy neural network is as follows:

[0144]

[0145] Among them, Loss t Rin represents the loss value in the t-th iteration. t This represents the ideal value in the t-th iteration. This represents the output result of the fuzzy output layer in the t-th iteration.

[0146] The first and second kinetic energy coefficients are set to correct the center value and width of the Gaussian membership function. The specific formulas are as follows:

[0147]

[0148] in, and Let α and β represent the center values ​​of the Gaussian membership functions of the nth fuzzy subset of the mth input in the (t-1)th and (t-2)th iterations, respectively. Let α represent the first kinetic coefficient, β represent the second kinetic coefficient, and Loss represent the loss value. mn The center value of the Gaussian membership function of the nth fuzzy subset of the mth input is represented. and σ represents the width of the Gaussian membership function of the nth fuzzy subset of the mth input in the (t-1)th and (t-2)th iterations, respectively. mnThe width of the Gaussian membership function of the nth fuzzy subset of the mth input is represented.

Claims

1. A mine explosion-proof frequency converter energy-saving optimization system, characterized in that: Specifically comprising: The host computer, the switch, the PID controller, the power distribution cabinet, the frequency converter, the driving motor, the belt conveyor, the laser radar sensor, the speed sensor and the intelligent frequency conversion module, the belt conveyor comprises a conveying belt, and the conveying belt conveys coal; The intelligent frequency conversion module specifically comprises: a coal flow calculation unit, an energy-saving optimization unit and a fuzzy control unit, and the coal flow calculation unit, the energy-saving optimization unit and the fuzzy control unit are sequentially and unidirectionally connected. The coal flow calculation unit calculates the coal flow through the laser radar sensor, and the specific steps are as follows: Step S1: obtaining laser point cloud data: emitting laser pulses to the belt conveyor through the laser radar sensor to obtain laser point cloud data of the coal, and the laser point cloud data specifically comprises a rotation angle of each laser point and a distance from each laser point to the laser radar sensor; Step S2: establishing a Cartesian coordinate system: taking the position of the laser radar sensor as the origin, taking the movement direction of the conveying belt as the Z axis, taking the scanning direction of the laser pulse with a rotation angle of 0 degrees as the X axis, and taking the direction perpendicular to the X axis and the Z axis as the Y axis; Step S3: constructing a coal cross-section diagram: taking the plane where the origin, the X axis and the Y axis are located as the OXY plane, and the coal cross-section diagram is composed of the laser point cloud data of the coal in the OXY plane; Step S4: denoising the laser point cloud data by using a K-means clustering algorithm combined with an adaptive threshold filtering algorithm; Step S5: calculating the area of the coal cross-section diagram; Step S6: calculating the coal flow, and the specific formula is as follows: ； wherein, is the coal flow rate, is the average density of the coal in kg / m 3 , is the frame rate of the lidar sensor in FPS, is the total number of coal cross-sections, is the running speed of the conveyor belt in m / s, is the area of the th coal cross-section in m 2 ; The specific steps of denoising the laser point cloud data by using the K-means clustering algorithm combined with the adaptive threshold filtering algorithm in step S4 are as follows: Step S41: clustering the laser point cloud data by using a K-means clustering algorithm; Step S42: calculating the local density of each laser point in the cluster by using a Gaussian kernel function, and the specific calculation formula is as follows: ； wherein, denotes a local density of laser points , denotes any cluster, and both denote any laser point in denotes and the Euclidean distance between denotes a width parameter of a Gaussian kernel function; Step S43: calculating the standard deviation of the local density of all laser points in the cluster, and taking three times the standard deviation as the adaptive threshold of the cluster; Step S44: removing the laser points in each cluster whose local density is outside the adaptive threshold of the cluster; The energy-saving optimization unit constructs an energy-saving optimization model based on a BP neural network to obtain the optimal speed under the condition that the coal flow is fixed, and the optimal speed is the running speed of the conveying belt when the power of the belt conveyor is the smallest.

2. The energy-saving optimization system of the mine explosion-proof frequency converter according to claim 1, characterized in that: The fuzzy control unit realizes real-time automatic and accurate control of the frequency signal of the frequency converter by using a PID control model based on a fuzzy neural network, and the specific steps are as follows: Step D1: obtaining the current running speed of the conveying belt through the speed sensor and calculating the current coal flow through the coal flow calculation unit; Step D2: obtaining the optimal speed corresponding to the current coal flow through the energy-saving optimization unit; Step D3: the difference between the optimal speed and the current running speed and the change rate of the difference are taken as input quantities, PID control parameters are obtained through calculation by a PID control model based on a fuzzy neural network, and the frequency converter is controlled by frequency conversion by using the PID control parameters.

3. The energy saving optimization system for mine explosion-proof frequency converter according to claim 2, characterized in that: The PID control model based on the fuzzy neural network specifically comprises a fuzzy input layer, a fuzzification layer, a fuzzy rule layer, a normalization layer and a fuzzy output layer.

4. The energy saving optimization system for mine explosion-proof frequency converter according to claim 3, characterized in that: The fuzzification layer constructs seven fuzzy subsets, and each fuzzy subset is fuzzified by a Gaussian membership function.

5. The energy saving optimization system for mine explosion-proof frequency converter according to claim 4, characterized in that: The PID control model based on the fuzzy neural network sets a first kinetic energy coefficient and a second kinetic energy coefficient, and corrects the center value of the Gaussian membership function and the width of the Gaussian membership function, and the specific formula is as follows: ； ； in, , and They represent the first The next iteration, the... The second iteration and the first The iteration of the ... The first input quantity The center value of the Gaussian membership function of a fuzzy subset Indicates the first kinetic energy coefficient. This represents the second kinetic energy coefficient. Indicates the loss value. Indicates the first The first input quantity The center value of the Gaussian membership function of a fuzzy subset , and They represent the first The next iteration, the... The second iteration and the first The iteration of the ... The first input quantity The width of the Gaussian membership function of a fuzzy subset. Indicates the first The first input quantity The width of the Gaussian membership function of a fuzzy subset.

Images