Discrete bayesian filtering based shearer relative position positioning system and method

Abstract

The application provides a shearer relative position positioning system and method based on discrete Bayesian filtering, and belongs to the technical field of shearer positioning; the application solves the problems of frame loss and frame jump existing in the positioning result of the infrared sensing technology used in the current shearer positioning; the application comprises a shearer, an inertial navigation positioning device, an infrared signal transmitter and an infrared signal receiver; the inertial navigation positioning device sends the processed real-time angular velocity and real-time acceleration data of the shearer to a crossheading master computer; an electro-hydraulic controller on a different hydraulic support performs algorithm processing on the received real-time shearer infrared position information; after the crossheading master computer receives the latest shearer position information, the crossheading master computer combines the inertial navigation positioning change between the last shearer position information and the latest shearer position information, adopts a discrete Bayesian filtering algorithm, and calculates the shearer relative position fusion positioning information; the application is applied to shearer position calculation.

Description

TECHNICAL FIELD

[0001] The application provides a shearer relative position positioning system and method based on discrete Bayesian filtering, and belongs to the technical field of shearer position positioning. BACKGROUND

[0002] The current methods for shearer relative position positioning in fully mechanized coal mining faces include shearer walking encoder and infrared sensor positioning, and strapdown inertial navigation system. The shearer walking encoder is an encoder installed on the traction part of the shearer to record the walking distance of the shearer. However, the shearer walking encoder has certain cumulative error, and needs to be corrected regularly during use. The infrared sensor positioning is to install an infrared emitter on the shearer and install an infrared receiver on each hydraulic support. When the shearer passes through the hydraulic support, the infrared receiver on the hydraulic support receives the signal and determines the position of the shearer relative to the hydraulic support. Due to the problems such as shielding and direction deflection of the infrared sensor, the shearer positioning may lose the support or jump the support. The strapdown inertial navigation system can record the running trajectory of the shearer, but needs to be calibrated by a position calibration algorithm at the beginning of each operation, and will have large cumulative error after a long time of operation.

[0003] Chinese invention patent (application number: CN201510870392.1) proposes a shearer positioning device and method based on inertial navigation and laser scanning fusion, which uses a fusion algorithm based on least square method-neural network algorithm to determine the position of the shearer and realizes accurate positioning. Chinese invention patent (application number: CN202011436943.0) proposes a shearer positioning error elimination method, which respectively eliminates the errors of the receiving module and the model to improve the positioning accuracy. Chinese invention patent (application number: CN202110124404.1) proposes a fully mechanized coal mining face shearer positioning method based on coded pattern recognition, which can quickly and accurately determine the position of the shearer in the fully mechanized coal mining face to a certain extent. Chinese invention patent (application number: CN202111507050.5) proposes a virtual-real fusion positioning system for a shearer based on a laser radar, which uses two laser radars, an inclination sensor and an odometer installed on the shearer to collect the attitude data of the support and the shearer, and can obtain the relative position information and the absolute position information of the shearer in the working face after solving. However, the above-mentioned patents have different degrees of defects such as complex algorithm or low precision. SUMMARY

[0004] The application proposes a shearer relative position positioning system and method based on discrete Bayesian filtering to solve the problems such as lost support and jumped support in the positioning results of the infrared sensor technology used in the current shearer positioning.

[0005] In order to solve the above technical problems, the technical scheme adopted by the present application is: a relative position positioning system of a coal mining machine based on a discrete Bayesian filter, comprising a coal mining machine, an inertial navigation positioning device, an infrared signal transmitter and an infrared signal receiver, wherein the inertial navigation positioning device is installed in an explosion-proof housing on the body of the coal mining machine, the infrared signal transmitter is installed on the coal mining machine, and the infrared signal receiver is installed on each hydraulic support column;

[0006] The inertial navigation positioning device sends the inertial navigation positioning result of the coal mining machine obtained by processing the real-time angular velocity and real-time acceleration data of the coal mining machine to the main control computer of the crossheading;

[0007] Each infrared signal receiver is connected with the electro-hydraulic controller on the hydraulic support where it is installed, and sends the position information of the coal mining machine to the electro-hydraulic controller of the hydraulic support;

[0008] The electro-hydraulic controllers on different hydraulic supports perform algorithm processing on the received real-time position information of the coal mining machine, and then publish the processed information to the electro-hydraulic control system network of the whole working face through a bus;

[0009] After receiving the latest position information of the coal mining machine returned by the electro-hydraulic controller, the main control computer of the crossheading combines the inertial navigation positioning change between the last position information of the coal mining machine and the latest position information of the coal mining machine, and uses a discrete Bayesian filter algorithm to calculate the relative position fusion positioning information of the coal mining machine.

[0010] The inertial navigation device comprises a three-axis gyroscope, a three-axis accelerometer and an inertial navigation microprocessor. During the operation of the coal mining machine, the inertial navigation positioning device measures the real-time angular velocity in three directions through the three-axis gyroscope, measures the real-time acceleration values in three directions through the three-axis accelerometer, samples the measurement data of the three-axis gyroscope and the three-axis accelerometer to the inertial navigation microprocessor, and connects the inertial navigation microprocessor with the main control computer of the crossheading through a serial interface.

[0011] The infrared signal transmitter continuously emits infrared signals when the coal mining machine is running, and the infrared signal receivers on multiple hydraulic supports near the coal mining machine simultaneously receive the infrared signals. The infrared signal receivers that receive the signals report the position signals of the coal mining machine to the electro-hydraulic controllers of the corresponding hydraulic supports.

[0012] A relative position positioning method of a coal mining machine based on a discrete Bayesian filter, which uses a relative position positioning system of a coal mining machine based on a discrete Bayesian filter, and comprises the following steps:

[0013] S1: statistics the measurement error of the position of the coal mining machine detected by the infrared sensor, and uses the measurement error as a system preset value;

[0014] S2: initialize the position confidence of the coal mining machine;

[0015] S3: Collecting the position signal of the coal mining machine measured by the infrared sensor;

[0016] S4: Calculating the transition probability of the relative position of the coal mining machine: the main control computer of the crossheading calculates the transition probability of the relative position of the coal mining machine according to the position information of the coal mining machine transmitted back at the latest time t i and the position information of the coal mining machine transmitted back at the last time t i-1 , intercepts the position change amount Δi of the coal mining machine between t i-1 and t i , and calculates the transition probability distribution of the relative position change of the coal mining machine according to Δi;

[0017] S5: Recurrent update: based on the position confidence of the coal mining machine at t i-1 and the transition probability of the position of the coal mining machine between t i-1 and t i , the position confidence of the coal mining machine at t i is updated to realize control update;

[0018] After the position of the coal mining machine is measured by the infrared sensor at t i , a measurement update matrix is established according to the measurement error probability of the infrared sensor measured in step S1 to realize measurement update and obtain a measurement update confidence matrix;

[0019] The main control computer of the crossheading performs control update and measurement update once every time the position of the coal mining machine is updated, and the support number of the coal mining machine position confidence with the maximum value in the measurement update confidence matrix is the support number of the coal mining machine position fusion positioning result at t i .

[0020] The measurement error of the infrared sensor in step S1 needs to be completed before the actual operation of the system, and the specific process is as follows:

[0021] Let Sense_X represent the position of the coal mining machine detected by the infrared sensor at t, and X represent the actual position of the coal mining machine at t. The measured measurement error includes:

[0022] The probability that the infrared sensor detects that the position of the coal mining machine at t is two supports larger than the actual position of the coal mining machine in the direction of the large support:

[0023] P(Sense_X=n|X=n-2);

[0024] The probability that the infrared sensor detects that the position of the coal mining machine at t is one support larger than the actual position of the coal mining machine in the direction of the large support:

[0025] P(Sense_X=n|X=n-1);

[0026] The probability that the infrared sensor detects that the position of the coal mining machine at t is correct:

[0027] P(Sense_X=n|X=n+1);

[0028] The probability that the infrared sensor detects that the position of the coal mining machine at time t is one frame to the small frame direction from the actual position of the coal mining machine:

[0029] P(Sense_X=n|X=n+1);

[0030] The probability that the infrared sensor detects that the position of the coal mining machine at time t is two frames to the small frame direction from the actual position of the coal mining machine:

[0031] P(Sense_X=n|X=n+2)。

[0032] The process of initializing the confidence of the position of the coal mining machine in the step S2 is as follows:

[0033] At the initial time t0, no measurement value is obtained, and it is considered that the probability of the coal mining machine being at any hydraulic support position is the same, i.e., P(X=n)=1 / m, m is the total number of hydraulic supports in the working face;

[0034] The confidence matrix of the position of the coal mining machine at time t0 is Bel(t=t0), and then:

[0035] Bel(t=t0)=[1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m……1 / m]。

[0036] The process of collecting the position information of the coal mining machine by the infrared sensor in the step S3 is as follows:

[0037] The infrared signal transmitter of the coal mining machine continuously emits infrared signals when the coal mining machine is running, and the infrared signal receivers on multiple hydraulic supports near the coal mining machine can simultaneously receive the infrared signals. The infrared signal receivers that receive the signals report the position signal of the coal mining machine to the electro-hydraulic controller of the hydraulic support.

[0038] The electro-hydraulic controllers on different hydraulic supports perform algorithm processing on the received real-time position information of the coal mining machine, obtain the position information of the coal mining machine with the strongest signal, and publish the position information of the coal mining machine with the strongest signal to the electro-hydraulic control system network of the entire working face through the bus, and finally transmit it back to the main control computer of the crossheading.

[0039] The calculation formula of the probability distribution of the relative position change of the coal mining machine in the step S4 is as follows:

[0040] The transition probability of the relative position change ΔX=0 of the coal mining machine, i.e., the transition probability of the relative position change of the coal mining machine:

[0041] P(ΔX=0)=f1(Δ i ).

[0042] Transition probability of the shearer relative position change ΔX=1, i.e. transition probability of the shearer relative position to the large frame direction 1 frame bias:

[0043] P(ΔX=1)=f2(Δ i );

[0044] Transition probability of the shearer relative position change ΔX=2, i.e. transition probability of the shearer relative position to the large frame direction 2 frame bias:

[0045] P(ΔX=2)=f3(Δ i );

[0046] Transition probability of the shearer relative position change ΔX=-1, i.e. transition probability of the shearer relative position to the small frame direction 1 frame bias:

[0047] P(ΔX=-1)=f4(Δ i );

[0048] Transition probability of the shearer relative position change ΔX=-2, i.e. transition probability of the shearer relative position to the small frame direction 2 frame bias:

[0049] P(ΔX=-2)=f5(Δ i ).

[0050] The step of controlling updating in the step 5 is as follows:

[0051] Let Bel(t=t i-1 )=[P(X=1) P(X=2) P(X=3)……P(X=m-2) P(X=m-1) P(X=m)], the control updating process is expressed as:

[0052]

[0053] The step of measurement updating in the step 5 is as follows:

[0054] After obtaining the shearer position measured by the infrared sensor at the moment t i , the measurement updating matrix M is established according to the infrared sensor measurement error probability counted in the step 1;

[0055] The expression of the measurement updating matrix M is as follows:

[0056] M=[0......0 P(SenseX=n|X=n-2) P(SenseX=n|X=n-1) P(SenseX=n|X=n) P(SenseX=n|X=n+1) P(SenseX=n|X=n+2) 0......0];

[0057] Where M is a 1×m row matrix;

[0058] Calculate the measurement update confidence matrix Bel(t=t) i )=[μ]Bel(t=t i M;

[0059] μ is the normalization constant.

[0060] The advantages of this invention compared to the prior art are as follows: This invention combines infrared sensing data and inertial navigation data to achieve fusion positioning. It adopts the discrete Bayesian filtering method to combine and fuse the two types of data, which improves the accuracy of the relative position positioning of the coal mining machine and hydraulic support, and is not affected by the cumulative error of inertial navigation positioning. Attached Figure Description

[0061] The present invention will be further described below with reference to the accompanying drawings:

[0062] Fig. 1 This is a schematic diagram of the structure of the system of the present invention arranged on the longwall mining face;

[0063] Fig. 2 This is a schematic diagram of the framework structure of the system of the present invention;

[0064] Fig. 3 This is a flowchart of the method of the present invention;

[0065] In the diagram: 1 is a hydraulic support, 2 is a coal mining machine, 3 is an inertial navigation and positioning device, 4 is an infrared signal transmitter, and 5 is an infrared signal receiver. Detailed Implementation

[0066] like Figs. 1 to 3 As shown, the present invention provides a relative position positioning system for a coal mining machine based on discrete Bayesian filtering, including a coal mining machine 2, an inertial navigation positioning device 3, an infrared signal transmitter 4, and an infrared signal receiver 5. The inertial navigation positioning device 3 is installed inside an explosion-proof shell on the body of the coal mining machine 2, the infrared signal transmitter 4 is installed on the coal mining machine 2, and the infrared signal receiver 4 is installed on the column of each hydraulic support 1.

[0067] The inertial navigation device 3 includes a three-axis gyroscope, a three-axis accelerometer, and an inertial navigation microprocessor. During the operation of the coal mining machine 2, the inertial navigation positioning device 3 measures the real-time angular velocity in three directions through the three-axis gyroscope and measures the real-time acceleration values ​​in three directions through the three-axis accelerometer. The measurement data from the three-axis gyroscope and the three-axis accelerometer are sampled to the inertial navigation microprocessor, which is connected to the main control computer of the roadway through a serial interface.

[0068] The infrared signal transmitter 4 continuously emits infrared signals when the coal mining machine 2 is running, and the infrared signal receivers 5 on the multiple hydraulic supports 1 near the coal mining machine 2 can simultaneously receive the infrared signals, and the infrared signal receivers 5 receiving the signals report the coal mining machine position signals to the electro-hydraulic controllers on the hydraulic supports 1. With the running of the coal mining machine 2, the electro-hydraulic controllers on the different hydraulic supports 1 perform algorithm processing on the real-time coal mining machine position information received, and then publish the information to the electro-hydraulic control system network of the whole working face through a bus.

[0069] After the main control computer of the crossheading receives the latest coal mining machine position information returned by the electro-hydraulic controller, the inertial navigation positioning change between the last coal mining machine position information and the latest coal mining machine position information is combined, and a discrete Bayesian filtering algorithm is used to calculate the relative position fusion positioning information of the coal mining machine.

[0070] The application also provides a coal mining machine relative position positioning method based on a discrete Bayesian filter, which comprises the following steps:

[0071] Step 1: Statistic measurement error of infrared sensor

[0072] The measurement error of the infrared sensor in detecting the position of the coal mining machine is calculated, wherein Sense_X represents the position of the coal mining machine detected by the infrared sensor at time t, X represents the actual position of the coal mining machine at time t, and the calculated measurement error comprises:

[0073] The probability that the infrared sensor detects that the position of the coal mining machine at time t is two supports to the large support direction from the actual position of the coal mining machine:

[0074] P(Sense_X=n|X=n-2);

[0075] The probability that the infrared sensor detects that the position of the coal mining machine at time t is one support to the large support direction from the actual position of the coal mining machine:

[0076] P(Sense_X=n|X=n-1);

[0077] The probability that the infrared sensor detects that the position of the coal mining machine at time t is correct:

[0078] P(Sense_X=n|X=n);

[0079] The probability that the infrared sensor detects that the position of the coal mining machine at time t is one support to the small support direction from the actual position of the coal mining machine:

[0080] P(Sense_X=n|X=n+1);

[0081] The probability that the infrared sensor detects that the position of the coal mining machine at time t is two supports to the small support direction from the actual position of the coal mining machine:

[0082] P(Sense_X = n | X = n + 2);

[0083] The statistical process must be completed before the positioning system is actually run, and the above measurement error is taken as the system preset value.

[0084] Step 2: Initialize the confidence of the position of the coal mining machine

[0085] At the initial time t0, no measurement value is obtained, and it can be considered that the probability of the coal mining machine being at any hydraulic support position is the same, P(X = n) = 1 / m, where m is the total number of hydraulic supports in the working face.

[0086] The confidence matrix of the position of the coal mining machine at the initial time t0 is Bel(t = t0), and thus

[0087] Bel(t = t0) = [1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m 1 / m …… 1 / m], which has m columns in the matrix.

[0088] Step 3: Collect the position of the coal mining machine measured by the infrared sensor

[0089] When the coal mining machine is running, the infrared signal transmitter continuously emits infrared signals, and the infrared signal receivers on multiple hydraulic supports near the coal mining machine can simultaneously receive the infrared signals. The infrared signal receivers that receive the signals report the position signal of the coal mining machine to the electro-hydraulic controller of the hydraulic support. The electro-hydraulic controller on different hydraulic supports processes the received real-time position information of the coal mining machine through an algorithm to obtain the position information of the coal mining machine with the strongest received infrared signal, and publishes the position information of the coal mining machine to the entire electro-hydraulic control system network of the working face through a bus, and finally returns to the main control computer of the crossheading.

[0090] Step 4: Calculate the transition probability of the relative position of the coal mining machine

[0091] The main control computer of the crossheading obtains the time t i of the latest transmission of the position information of the coal mining machine and the time t i-1 of the transmission of the position information of the coal mining machine last time, and intercepts the change Δi of the inertial navigation position of the coal mining machine between t i-1 and t i . According to Δi, the transition probability distribution of the relative position change of the coal mining machine is calculated. For a fully mechanized working face with a hydraulic support width of 1.5 m, the specific calculation formula is as follows.

[0092] The transition probability of the relative position change ΔX = 0 of the coal mining machine, i.e., the transition probability of no change in the relative position of the coal mining machine:

[0093]

[0094] Transition probability of the shearer relative position change ΔX = 1, i.e. transition probability of the shearer relative position to the large frame direction bias 1 frame:

[0095]

[0096] Transition probability of the shearer relative position change ΔX = 2, i.e. transition probability of the shearer relative position to the large frame direction bias 2 frame:

[0097]

[0098] Transition probability of the shearer relative position change ΔX = -1, i.e. transition probability of the shearer relative position to the small frame direction bias 1 frame:

[0099]

[0100] Transition probability of the shearer relative position change ΔX = -2, i.e. transition probability of the shearer relative position to the small frame direction bias 2 frame:

[0101]

[0102] Step 5: Loop update

[0103] 5.1 Control update

[0104] Based on the shearer position confidence Bel (t = t i-1 ) at time t i-1 and the transition probability of the shearer position from t i-1 to t i , the shearer position confidence Bel (t = t i ) at time t i is updated. This step is called control update in the Bayesian filtering.

[0105] Let Bel (t = t i-1 ) = [P(X = 1) P(X = 2) P(X = 3) … P(X = m-2) P(X = m-1) P(X = m)], the control update process is expressed as:

[0106]

[0107] 5.2 Measurement update

[0108] After obtaining the shearer position measured by the infrared sensor at time t i , the measurement update matrix M is established according to the infrared sensor measurement error probability counted in step 1.

[0109] The expression of the measurement update matrix M is as follows:

[0110] M=[0......0 P(SenseX=n|X=n-2) P(SenseX=n|X=n-1) P(SenseX=n|X=n) P(SenseX=n|X=n+1) P(SenseX=n|X=n+2) 0......0]; M is a 1xm row matrix;

[0111] The measurement confidence matrix Bel(t=t i ) is calculated. i )M.

[0112] The product result is usually no longer a probability, the sum can not be 1, so the result needs to be normalized by the normalization constant μ.

[0113] The control update and the measurement update are performed once for each time the gateway computer receives a position update of the coal mining machine, and the maximum value of the confidence of the position of the coal mining machine in the measurement confidence matrix Bel(t=t i ) is the support number of the hydraulic support where the position fusion result of the coal mining machine at the time t i is located.

[0114] It should be noted that the connection relationship between the components and modules of the present application is definite and achievable. Except for the special description in the embodiments, the specific connection relationship can bring corresponding technical effects, and based on the premise of not relying on the execution of the corresponding software program, the technical problems proposed by the present application are solved. The model of the components, modules, specific elements, the connection mode between them, and the conventional use method and the expected technical effects brought by the above technical features, except for the specific description, all belong to the public content disclosed in the patents, journal papers, technical manuals, technical dictionaries, textbooks, and other existing technologies before the application date, or belong to the conventional technology and common knowledge in the art, and do not need to be described in detail. The technical solutions provided by the present application are clear, complete, and achievable, and the corresponding physical products can be reproduced or obtained according to the technical means.

[0115] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent substitutions for part or all of the technical features; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for positioning relative position of a coal mining machine based on discrete Bayesian filtering, characterized in that: The method comprises the following steps: S1: statistics of the measurement error of the infrared sensor detecting the position of the coal mining machine, and taking the measurement error as a system preset value; S2: initialization of the position confidence of the coal mining machine; S3: acquisition of the position signal of the coal mining machine measured by the infrared sensor; S4: Shearer relative position transition probability calculation: according to the latest shearer position information transmission time t i and the last shearer position information transmission time t i-1 , intercept the shearer inertial navigation position change Δi between t i-1 and t i , calculate the transition probability distribution of shearer relative position change according to Δi; S5: cyclic update: update the confidence of the position of the shearer at time t based on the position of the shearer at time t i-1 the transition probability of the position of the shearer at time t i-1 to the position of the shearer at time t i the position of the shearer at time t i the confidence of the position of the shearer at time t, and implement control update; Obtain t i After the infrared sensor measures the position of the coal mining machine, a measurement update matrix is established according to the measurement error probability of the infrared sensor in step S1, measurement updating is realized, and a measurement update confidence matrix is obtained. The main control computer of the crossheading updates control and measurement every time the position of the coal mining machine is updated, and the support number of the hydraulic support with the maximum value of the confidence level of the coal mining machine in the confidence level matrix of the measurement is t i The fusion positioning result of the position of the coal mining machine is obtained in real time.

2. The method according to claim 1, wherein: The measurement error of the infrared sensor in the step S1 needs to be completed before the actual operation of the system, and the specific process is as follows: Let Sense_X represent the position of the coal mining machine detected by the infrared sensor at t time, X represent the actual position of the coal mining machine at t time, and the measured measurement error includes: The probability that the infrared sensor detects that the position of the coal mining machine at t time is two frames larger than the actual position of the coal mining machine in the large frame direction: P(Sense_X=n|X=n-2); The probability that the infrared sensor detects that the position of the coal mining machine at t time is one frame larger than the actual position of the coal mining machine in the large frame direction: P(Sense_X=n|X=n-1); The probability that the infrared sensor detects that the position of the coal mining machine at t time is correct: P(Sense_X=n|X=n); The probability that the infrared sensor detects that the position of the coal mining machine at t time is one frame smaller than the actual position of the coal mining machine in the small frame direction: P(Sense_X=n|X=n+1); The probability that the infrared sensor detects that the position of the coal mining machine at t time is two frames smaller than the actual position of the coal mining machine in the small frame direction: P(Sense_X=n|X=n+2).

3. The method according to claim 2, wherein: The process of initializing the position confidence of the coal mining machine in the step S2 is as follows: At the initial t0 time, no measurement value is obtained, and it is considered that the probability of the coal mining machine being at any hydraulic support position is the same, i.e. P(X=n)=1 / m, m is the total number of hydraulic supports in the working face; The position confidence matrix of the coal mining machine at t0 time is Bel(t=t0), and then: 。 4. The method according to claim 3, characterized in that: The process of the infrared sensor collecting the position information of the coal mining machine in the step S3 is as follows: When the coal mining machine is running, the infrared signal transmitter continuously emits infrared signals, and the infrared signal receivers on multiple hydraulic supports near the coal mining machine can simultaneously receive the infrared signals, and the infrared signal receivers receiving the signals report the position signal of the coal mining machine to the electro-hydraulic controller of the hydraulic support; The electro-hydraulic controllers on different hydraulic supports perform algorithm processing on the received real-time position information of the coal mining machine, obtain the position information of the coal mining machine with the strongest received infrared signal, and publish the position information of the coal mining machine with the strongest signal to the electro-hydraulic control system network of the whole working face through the bus, and finally transmit back to the main control computer of the crossheading.

5. The method according to claim 4, characterized in that: The calculation formula of the probability distribution of the relative position change of the coal mining machine in the step S4 is as follows: The transition probability of the relative position change ΔX=0 of the coal mining machine, i.e. the transition probability of the relative position of the coal mining machine without change: P(ΔX=0) = f1(Δ i ); The transition probability of the relative position change ΔX=1 of the coal mining machine, i.e. the transition probability of the relative position of the coal mining machine to the large frame direction by 1 frame: P(ΔX=1)=f2(Δ i ); The transition probability of the relative position change ΔX=2 of the coal mining machine, i.e. the transition probability of the relative position of the coal mining machine to the large frame direction by 2 frames: P(ΔX=2) = f3(Δ i ); The transition probability of the relative position change ΔX=-1 of the coal mining machine, i.e. the transition probability of the relative position of the coal mining machine to the small frame direction by 1 frame: P(ΔX=-1)=f4(Δ i ); Transition probability of the relative position change of the coal mining machine ΔX=-2, i.e. transition probability of the relative position of the coal mining machine to the small size frame direction by 2 frames: P(ΔX=-2) = f5(Δ i ).

6. The method according to claim 5, wherein: The step of updating in the step 5 is as follows: Let , the control update process is represented as: 。 7. The method according to claim 6, characterized in that: The step of measuring in the step 5 is as follows: get t i After the infrared sensor measures the position of the coal mining machine, a measurement update matrix M is established according to the measurement error probability of the infrared sensor in step 1. The expression of the measurement update matrix M is as follows: ； Where M is a 1xm row matrix; The computed measurement update confidence matrix Bel(t = t i ) = [μ] Bel (t = t i ) M; μ is a normalization constant.

8. A relative position location system for a coal mining machine based on a discrete Bayesian filter, characterized by: The system adopts the relative position positioning method of the coal mining machine based on the discrete Bayesian filtering in any one of claims 1-7 to calculate the position of the coal mining machine, and the system comprises the coal mining machine, an inertial navigation positioning device, an infrared signal transmitter and an infrared signal receiver, wherein the inertial navigation positioning device is installed in an explosion-proof housing on the body of the coal mining machine, the infrared signal transmitter is installed on the coal mining machine, and the infrared signal receiver is installed on each hydraulic support column; The inertial navigation positioning device sends the inertial navigation positioning result of the coal mining machine obtained by processing the real-time angular velocity and real-time acceleration data of the coal mining machine to the main control computer of the crossheading; Each infrared signal receiver is connected with the electro-hydraulic controller on the hydraulic support where it is installed, and sends the position information of the coal mining machine to the electro-hydraulic controller of the hydraulic support; The electro-hydraulic controllers on different hydraulic supports perform algorithm processing on the received real-time position information of the coal mining machine, and then publish the position information to the electro-hydraulic control system network of the whole working face through a bus; After receiving the latest position information of the coal mining machine returned by the electro-hydraulic controller, the main control computer of the crossheading combines the inertial navigation positioning change between the last position information of the coal mining machine and the latest position information of the coal mining machine, and calculates the fused positioning information of the relative position of the coal mining machine by using the discrete Bayesian filtering algorithm.

9. A shearer relative position positioning system based on discrete Bayesian filtering according to claim 8, characterized in that: The inertial navigation positioning device comprises a three-axis gyroscope, a three-axis accelerometer and an inertial navigation microprocessor. During the operation of the coal mining machine, the inertial navigation positioning device measures the real-time angular velocity in three directions through the three-axis gyroscope, measures the real-time acceleration values in three directions through the three-axis accelerometer, and samples the measurement data of the three-axis gyroscope and the three-axis accelerometer to the inertial navigation microprocessor. The inertial navigation microprocessor is connected with the main control computer of the crossheading through a serial interface.

10. A shearer relative position positioning system based on discrete Bayesian filtering according to claim 9, characterized in that: The infrared signal transmitter continuously emits infrared signals when the coal mining machine is running. The infrared signal receivers on multiple hydraulic supports near the coal mining machine simultaneously receive the infrared signals. The infrared signal receivers that receive the signals report the position signals of the coal mining machine to the electro-hydraulic controllers of the corresponding hydraulic supports.

Images