Unmanned mine car braking system fault diagnosis method based on model identification

Abstract

The invention belongs to the technical field of fault diagnosis, and provides an unmanned mine car braking system fault diagnosis method based on model identification. According to the diagnosis method, a brake system reference model is established by adopting a model identification method based on a large amount of normal driving data accumulated in historical operation of the unmanned mine car, and whether a fault occurs or not is judged by calculating the deviation between brake system model output and brake system reference model output. The problem that the traditional fault detection depends on artificial experience and lacks reliable reference is solved, and the accuracy of fault detection can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a fault diagnosis method for a brake system of an unmanned mining vehicle based on model identification. Background Art

[0002] The working environment in the mining area is harsh. Once a mine car breaks down, it must be diagnosed quickly and appropriate measures must be taken to avoid catastrophic consequences. The braking system is responsible for the deceleration and emergency braking of the mine car. It is one of the most critical systems of the mine car. The braking performance directly affects the safety of the mine car and even the entire mining area. For unmanned mine cars, their working stability is more dependent on the execution performance of each system of the vehicle. Therefore, the safety of the braking system of unmanned mine cars is particularly important.

[0003] The braking system of an unmanned mining vehicle usually consists of electric brakes and mechanical hydraulic brakes, which work together to achieve high-performance braking of the vehicle. While this braking method saves energy and improves braking performance, it also increases the probability of failure. Therefore, accurate and timely fault diagnosis for unmanned mining vehicles can maximize the safety and operating efficiency of the vehicle. In the prior art, fault diagnosis of vehicle braking systems generally uses artificial perception or threshold-based diagnosis methods, which generally have problems such as low diagnostic efficiency, delayed diagnosis and inaccuracy. Summary of the invention

[0004] In view of the deficiencies in the above-mentioned prior art, the present invention proposes a fault diagnosis method for the braking system of an unmanned mine car based on model identification. The diagnostic method effectively utilizes a large amount of historical data accumulated during vehicle operation to identify the reference model of the braking system, thereby realizing accurate and rapid fault diagnosis of the braking system of the unmanned mine car, and providing a strong guarantee for the stable and efficient operation of the unmanned mine car.

[0005] The technical solution of the present invention is as follows:

[0006] A fault diagnosis method for the brake system of an unmanned mining vehicle based on model identification comprises the following steps:

[0007] Step S1: Collecting historical normal driving data of the unmanned mining vehicle during its historical operation;

[0008] Step S2: Establish a braking system model of the unmanned mining vehicle, determine the input parameters and output parameters of the braking system model, the input parameters include the electric braking control amount and the mechanical braking control amount, and the output parameter is the effective deceleration of the vehicle; simplify the braking system model into a second-order control system model, and its transfer function is expressed as:

[0009]

[0010] Where, s is the Laplace operator, Y(s) is the output of the second-order control system model, that is, the Laplace transform of the effective deceleration of the vehicle, U(s) is the input of the second-order control system model, that is, the Laplace transform of the vector composed of the electric brake control quantity and the mechanical brake control quantity, ω represents the natural oscillation frequency of the second-order control system model, and ζ is the damping ratio of the second-order control system model;

[0011] Step S3: Calculate the effective deceleration of the vehicle based on the speed and slope in the historical normal driving data, and use the Matlab parameter identification toolbox to identify ω and ζ of the second-order control system model based on the electric brake control amount, mechanical brake control amount and effective deceleration of the vehicle in the historical normal driving data, thereby obtaining a reference model of the braking system;

[0012] Step S4: setting a fault threshold according to the deviation between the actual vehicle effective deceleration output by the braking system model and the reference vehicle effective deceleration output by the braking system reference model during the operation of the unmanned mining vehicle, setting a diagnostic rule for the fault type, and establishing a rule base;

[0013] Step S5: When the unmanned mining vehicle is traveling, the real-time electric brake control amount and the mechanical brake control amount are respectively input into the brake system model and the brake system reference model to obtain the actual vehicle effective deceleration and the reference vehicle effective deceleration, and then the deviation between the two is calculated;

[0014] Step S6: Based on the deviation between the reference vehicle effective deceleration and the actual vehicle effective deceleration, identify the fault type according to the diagnostic rules; if an unidentifiable fault type occurs, add the fault type and diagnostic rules according to the actual fault situation.

[0015] Preferably, the calculation method of the effective deceleration of the vehicle in step S3 is as follows:

[0016] (1) Calculate vehicle deceleration using a first-order Kalman filter:

[0017] v k,t =(v k,t-1 +0.053*a k,t-1 )+0.23476*(v t -(v k,t-1 +0.053*a k,t-1 ))

[0018] a k,t =-(a k,t-1 +0.55325*(v t -(v k,t-1 +0.053*a k,t-1 )))

[0019] Among them, v t is the vehicle speed at time t, vk,t 、v k,t-1 are the Kalman filter speeds at time t and t-1, respectively, and a k,t 、a k,t-1 are the Kalman filter decelerations at time t and t-1, respectively, and v k,t By v k,t-1 、a k,t-1 Iterative calculation, v k,0 =0, a k,0 =0,a k,t That is, the calculated vehicle deceleration at time t;

[0020] (2) Considering the slope resistance and sliding resistance, calculate the effective deceleration of the vehicle:

[0021]

[0022] a e,t =max(0,a k,t -a b,t )

[0023] Among them, a b is the deceleration caused by the slope and sliding resistance, f is the slope, g is the acceleration of gravity, max(0,a k,t -a b,t ) means taking 0 and a k,t -a b,t The maximum value between e,t is the calculated effective deceleration of the vehicle.

[0024] Preferably, the diagnostic rules in the rule base are as follows:

[0025] (1) If the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 60% of the reference vehicle effective deceleration, the fault type is determined to be insufficient braking;

[0026] (2) If the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 30% of the reference vehicle effective deceleration, the fault type is determined to be brake failure;

[0027] (3) When the following conditions are met: the brake opening control amount is 0 and the actual vehicle effective deceleration is greater than 0, the fault type is determined to be abnormal braking.

[0028] Preferably, the step S5 specifically includes:

[0029] Step S5-1: Input the real-time electric brake control amount and mechanical brake control amount into the brake system reference model to obtain the reference vehicle effective deceleration am,t ;

[0030] Step S5-2: Input the real-time electric brake control amount and mechanical brake control amount into the brake system model to obtain the actual vehicle effective deceleration a e,t ;

[0031] Step S5-3: Calculate the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation r, when the reference vehicle effective deceleration a m,t Greater than the actual vehicle effective deceleration a e,t , the deviation is the difference between the two, otherwise the deviation is 0:

[0032]

[0033] Preferably, the step S6 specifically includes:

[0034] Step S6-1: According to the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation r of the matching rule base;

[0035] Step S6-2: If the match is successful, the identified fault type is output;

[0036] Step S6-3: If the match fails, but the vehicle braking performance is manually determined to have a fault, a new diagnostic rule is added to the rule base based on the actual fault type manually detected and the corresponding driving data.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The present invention proposes a method for diagnosing brake system faults of unmanned mine vehicles based on model identification. Based on a large amount of normal driving data accumulated from the historical operation of unmanned mine vehicles, a brake system reference model is established by using a model identification method. By calculating the deviation between the brake system model output and the brake system reference model output, it is determined whether a fault occurs. This solves the problem of relying on manual experience and lack of reliable reference in traditional fault detection, and can improve the accuracy of fault detection.

[0039] 2. The present invention proposes a method for diagnosing the brake system fault of an unmanned mine car based on model identification. The method defines the possible fault types of the brake system based on experience, and realizes the fault diagnosis of the brake system in an inferential manner by analyzing the deviation between the brake system model output and the brake system reference model output. The method combines experience with data analysis to achieve efficient diagnosis in the event of vehicle failure, thereby maximizing the safety and operating efficiency of the unmanned mine car. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. The features and advantages of the present invention can be more clearly understood by referring to the drawings. The drawings are schematic and should not be understood as limiting the present invention in any way. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 The present invention is a flow chart of a method for diagnosing a fault of a brake system of an unmanned mining vehicle based on model identification.

[0042] Figure 2 It is a rule base and diagnostic reasoning flowchart.

[0043] Figure 3 It is the deceleration instruction of a certain unmanned mining truck in a certain period of time in Example 1.

[0044] Figure 4 is the effective deceleration of the reference vehicle in Example 1.

[0045] Figure 5 It is the actual effective vehicle deceleration of a certain unmanned mining truck in a certain period of time in Example 1.

[0046] Figure 6 It is the deviation between the reference vehicle effective deceleration and the actual vehicle effective deceleration of a certain unmanned mining truck in a certain period of time in Example 1. DETAILED DESCRIPTION

[0047] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0049] Example 1

[0050] A fault diagnosis method for the brake system of an unmanned mining vehicle based on model identification, such as Figure 1 As shown, the specific steps include:

[0051] Step S1: Collect historical normal driving data of the unmanned mining vehicle during its historical operation.

[0052] Step S2: Establish a braking system model of the unmanned mining vehicle, and determine the input parameters and output parameters of the braking system model. The input parameters include the electric braking control amount and the mechanical braking control amount, and the output parameter is the effective deceleration of the vehicle. The braking system model is simplified to a second-order control system model, and its transfer function is expressed as:

[0053]

[0054] Where, s is the Laplace operator, Y(s) is the output of the second-order control system model, that is, the Laplace transform of the effective deceleration of the vehicle, U(s) is the input of the second-order control system model, that is, the Laplace transform of the vector composed of the electric brake control quantity and the mechanical brake control quantity, which represents the natural oscillation frequency of the second-order control system model, and ζ is the damping ratio of the second-order control system model;

[0055] Since the effective deceleration of the vehicle cannot be measured directly, the effective deceleration of the vehicle is calculated by the vehicle speed and slope. The specific calculation method is as follows:

[0056] (1) Calculate vehicle deceleration using a first-order Kalman filter:

[0057] v k,t =(v k,t-1 +0.053*a k,t-1 )+0.23476*(v t -(v k,t-1 +0.053*a k,t-1 ))

[0058] a k,t =-(a k,t-1 +0.55325*(v t -(v k,t-1 +0.053*a k,t-1 )))

[0059] Among them, v t is the vehicle speed at time t, v k,t 、v k,t-1 are the Kalman filter speeds at time t and t-1, respectively, and a k,t 、a k,t-1 are the Kalman filter decelerations at time t and t-1, respectively, and v k,t By v k,t-1 、a k,t-1 Iterative calculation, v k,0 =0, a k,0 =0,a k,t This is the calculated vehicle deceleration at time t.

[0060] (2) Considering the slope resistance and sliding resistance, calculate the effective deceleration of the vehicle:

[0061]

[0062] a e,t =max(0,a k,t -a b,t )

[0063] Among them, a b is the deceleration caused by the slope and sliding resistance, f is the slope, g is the acceleration of gravity, max(0,a k,t -a b,t ) means taking 0 and a k,t -a b,t The maximum value between e,t is the calculated effective deceleration of the vehicle.

[0064] Step S3: Calculate the effective deceleration of the vehicle based on the speed and slope in the historical normal driving data. Based on the electric brake control amount, mechanical brake control amount and effective deceleration of the vehicle in the historical normal driving data, use the MATLAB parameter identification toolbox to identify ω and ζ of the second-order control system model, thereby obtaining a reference model of the braking system.

[0065] The brake system reference model outputs the effective deceleration of the vehicle under normal driving according to the electric brake control amount, mechanical brake control amount, vehicle speed and slope.

[0066] Step S4: setting a fault threshold according to the deviation between the actual vehicle effective deceleration output by the braking system model during the operation of the unmanned mining vehicle and the reference vehicle effective deceleration output by the braking system reference model, and setting a diagnostic rule for the fault type based on experience to establish a rule base.

[0067] like Figure 2 Specifically, based on the empirical definition of fault types and reasoning logic, the established diagnostic rules are as follows:

[0068] (1) If the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 60% of the reference vehicle effective deceleration, the fault type is determined to be insufficient braking.

[0069] (2) When the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 30% of the reference vehicle effective deceleration, the fault type is determined to be brake failure.

[0070] (3) When the following conditions are met: the brake opening control amount is 0 and the actual vehicle effective deceleration is greater than 0, the fault type is determined to be abnormal braking.

[0071] Step S5: When the unmanned mining car is traveling, the real-time electric brake control amount and the mechanical brake control amount are respectively input into the brake system model and the brake system reference model to obtain the actual vehicle effective deceleration and the reference vehicle effective deceleration, and then calculate the deviation between the two.

[0072] Step S5-1: Input the real-time electric brake control amount and mechanical brake control amount into the brake system reference model to obtain the reference vehicle effective deceleration a m,t . Figure 3 The figure shows the deceleration command of an unmanned mining truck in a certain period of time, which is the sum of the electric brake control amount and the mechanical brake control amount. It is input into the reference model of the braking system to obtain the following: Figure 4 The effective deceleration of the reference vehicle is shown.

[0073] Step S5-2: Input the real-time electric brake control amount and mechanical brake control amount into the brake system model to obtain the actual vehicle effective deceleration a e,t . Figure 5 The figure shows the actual effective vehicle deceleration of an unmanned mining truck during a certain period of time.

[0074] Step S5-3: Calculate the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation r, when the reference vehicle effective deceleration a m,t Greater than the actual vehicle effective deceleration a e,t , the deviation is the difference between the two, otherwise the deviation is 0:

[0075]

[0076] Figure 6 The figure shows the deviation between the effective deceleration of the reference vehicle and the actual vehicle during a certain period of time of an unmanned mining truck, as well as the corresponding thresholds of insufficient braking and braking failure.

[0077] Step S6: Based on the deviation between the reference vehicle effective deceleration and the actual vehicle effective deceleration, identify the fault type according to the diagnostic rules; if an unidentifiable fault type occurs, add the fault type and diagnostic rules according to the actual fault situation.

[0078] Specifically,

[0079] Step S6-1: According to the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation matches the diagnostic rules in the rule base.

[0080] Step S6-2: If the match is successful, the identified fault type is output. Figure 6As shown, according to the rule base, the brake under-threshold is 60% of the reference effective deceleration, and the brake failure threshold is 30% of the reference effective deceleration. The deviation r is about 14:26:075 to 14:26:115, the actual effective deceleration is lower than the brake under-threshold and meets more than 3 seconds, which meets the brake under-diagnosis rule, and the brake under-fault alarm is issued at this time.

[0081] Step S6-3: If the match fails, but the vehicle braking performance is manually determined to have a fault, a new diagnostic rule is added to the rule base based on the actual fault type manually detected and the corresponding driving data.

[0082] The method described in this embodiment can effectively solve the problem of low efficiency and poor accuracy of fault diagnosis in traditional methods. Based on the reference model of the braking system, the deviation between the actual output of the braking system model and the output of the reference model of the braking system is calculated to determine whether a fault has occurred, thereby improving the accuracy of fault detection; based on experience, the possible fault types of the braking system are defined, and by analyzing the deviation data, the fault diagnosis of the braking system is realized in an inferential manner, achieving efficient diagnosis in the case of vehicle faults, and maximizing the safety and operating efficiency of the vehicle.

[0083] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0084] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0085] In the present invention, the terms "first", "second", "third", "fourth" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance. The term "plurality" refers to two or more, unless otherwise clearly defined.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fault diagnosis method for the brake system of an unmanned mining vehicle based on model identification, characterized in that: The following steps are involved: Step S1: Collecting historical normal driving data of the unmanned mining vehicle during its historical operation; Step S2: Establish a braking system model of the unmanned mining vehicle, determine the input parameters and output parameters of the braking system model, the input parameters include the electric braking control amount and the mechanical braking control amount, and the output parameter is the effective deceleration of the vehicle; simplify the braking system model into a second-order control system model, and its transfer function is expressed as: Where, s is the Laplace operator, Y(s) is the output of the second-order control system model, that is, the Laplace transform of the effective deceleration of the vehicle, U(s) is the input of the second-order control system model, that is, the Laplace transform of the vector composed of the electric brake control quantity and the mechanical brake control quantity, ω represents the natural oscillation frequency of the second-order control system model, and ζ is the damping ratio of the second-order control system model; Step S3: Calculate the effective deceleration of the vehicle based on the speed and slope in the historical normal driving data, and use the Matlab parameter identification toolbox to identify ω and ζ of the second-order control system model based on the electric brake control amount, mechanical brake control amount and effective deceleration of the vehicle in the historical normal driving data, thereby obtaining a reference model of the braking system; Step S4: setting a fault threshold according to the deviation between the actual vehicle effective deceleration output by the braking system model and the reference vehicle effective deceleration output by the braking system reference model during the operation of the unmanned mining vehicle, setting a diagnostic rule for the fault type, and establishing a rule base; Step S5: When the unmanned mining vehicle is traveling, the real-time electric brake control amount and the mechanical brake control amount are respectively input into the brake system model and the brake system reference model to obtain the actual vehicle effective deceleration and the reference vehicle effective deceleration, and then the deviation between the two is calculated; Step S6: Based on the deviation between the reference vehicle effective deceleration and the actual vehicle effective deceleration, identify the fault type according to the diagnostic rules; if an unidentifiable fault type occurs, add the fault type and diagnostic rules according to the actual fault situation.

2. The method for diagnosing faults in the brake system of an unmanned mining vehicle according to claim 1, characterized in that: The calculation method of the effective deceleration of the vehicle in step S3 is as follows: (1) Calculate vehicle deceleration using a first-order Kalman filter: in k,t =(in k,t-1 +0.053*a k,t-1 )+0.23476*(in t -(in k,t-1 +0.053*a k,t-1 )) and k,t =-(a k,t-1 +0.55325*(in t -(in k,t-1 +0.053*a k,t-1 ))) Among them, v t is the vehicle speed at time t, v k,t 、v k,t-1 are the Kalman filter speeds at time t and t-1, respectively, and a k,t 、a k,t-1 are the Kalman filter decelerations at time t and t-1, respectively, and v k,t By v k,t-1 、a k,t-1 Iterative calculation, v k,0 =0, a k,0 =0,a k,t That is, the calculated vehicle deceleration at time t; (2) Considering the slope resistance and sliding resistance, calculate the effective deceleration of the vehicle: a e,t =max(0,a k,t -a b,t ) Among them, a b is the deceleration caused by the slope and sliding resistance, f is the slope, g is the acceleration of gravity, max(0,a k,t -a b,t ) means taking 0 and a k,t -a b,t The maximum value between e,t is the calculated effective deceleration of the vehicle.

3. The method for diagnosing faults in the brake system of an unmanned mining vehicle according to claim 1, characterized in that: The diagnostic rules in the rule base are as follows: (1) If the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 60% of the reference vehicle effective deceleration, the fault type is determined to be insufficient braking; (2) If the following conditions are met: within a period of 5 seconds, there is a period of more than 3 seconds, the brake opening control amount is greater than 0.4, and the actual vehicle effective deceleration is less than 30% of the reference vehicle effective deceleration, the fault type is determined to be brake failure; (3) When the following conditions are met: the brake opening control amount is 0 and the actual vehicle effective deceleration is greater than 0, the fault type is determined to be abnormal braking.

4. The method for diagnosing faults in the brake system of an unmanned mining vehicle according to claim 1, characterized in that: The step S5 specifically includes: Step S5-1: Input the real-time electric brake control amount and mechanical brake control amount into the brake system reference model to obtain the reference vehicle effective deceleration a m,t ; Step S5-2: Input the real-time electric brake control amount and mechanical brake control amount into the brake system model to obtain the actual vehicle effective deceleration a e,t ; Step S5-3: Calculate the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation r, when the reference vehicle effective deceleration a m,t Greater than the actual vehicle effective deceleration a e,t , the deviation is the difference between the two, otherwise the deviation is 0:

5. The method for diagnosing faults in the brake system of an unmanned mining vehicle according to claim 1, characterized in that: The step S6 specifically includes: Step S6-1: According to the actual vehicle effective deceleration a e,t and the reference vehicle effective deceleration a m,t The deviation r of the matching rule base; Step S6-2: If the match is successful, the identified fault type is output; Step S6-3: If the match fails, but the vehicle braking performance is manually determined to have a fault, a new diagnostic rule is added to the rule base based on the actual fault type manually detected and the corresponding driving data.

Images