A monitoring method for the steering system of an unmanned mining truck based on transmission ratio signals

Abstract

This invention relates to the field of unmanned mining trucks, specifically to a method for monitoring the steering system of an unmanned mining truck based on transmission ratio signals. First, a transmission ratio model is established based on collected data to predict the standard load transmission ratio and two transmission ratio threshold curves. Then, the vehicle's operational task information is confirmed, and the current vehicle's transmission ratio model is read. Next, the operating information of the steering subsystem and the actual operating transmission ratio are read. Finally, a predetermined decay judgment strategy is used to determine whether the steering subsystem is operating normally. If it is operating normally, the above steps continue until the task is completed. If it is not operating normally, the system will issue a warning and recalibrate the transmission subsystem. This invention can automatically adjust the transmission ratio thresholds, adapt to changes in various operating environments, reduce false alarms, and effectively monitor the operating status of the steering subsystem.

Description

Technical Field

[0001] This invention relates to the field of unmanned mining trucks, and more specifically to a method for monitoring the steering system of an unmanned mining truck based on a transmission ratio signal. Background Technology

[0002] The steering subsystem of an unmanned mining truck is one of its core components, directly impacting the truck's safety and efficiency. In the operation of unmanned transportation systems in open-pit mines, truck fault monitoring is crucial, typically relying on a transmission ratio threshold to determine the steering subsystem's status. The transmission ratio is the ratio between the input angular velocity (generated by the steering motor or other drive equipment) and the output angular velocity (achieved at the wheels) of the steering subsystem. Changes in this ratio reflect the operating status of the steering subsystem. During unmanned mining truck operation, as mileage increases, load and speed constantly change, causing variations in the load transmission ratio. For an unmanned mining truck in a fixed operating environment, all factors ultimately manifest in the steering subsystem's transmission ratio during operation; therefore, monitoring changes in the transmission ratio signal can reflect the steering subsystem's mileage status.

[0003] In existing technologies, monitoring the steering subsystem of unmanned mining trucks typically involves inputting multiple first-sampled transmission ratios and multiple second-sampled transmission ratios into a filter and fusing them to obtain the steering subsystem transmission ratio corresponding to a specific angle. This process is then repeated to obtain the steering subsystem transmission ratio for each angle. Furthermore, it is necessary to set transmission ratio thresholds for different types of mining trucks and load parameters.

[0004] However, existing monitoring methods for the steering subsystem of unmanned mining trucks have several problems. First, this method requires resetting threshold parameters for each angle and cannot adapt to changes in various operating environments. Second, due to variations in load and vehicle speed, the transmission ratio threshold is difficult to synchronize in real time, leading to false alarms and hindering effective monitoring of the steering subsystem's operating status. Finally, this method requires setting transmission ratio thresholds for different types of mining trucks and load parameters, increasing the complexity and workload of threshold setting. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a method for monitoring the steering system of an unmanned mining truck based on transmission ratio signals.

[0006] The method includes:

[0007] Step 1: Construct a transmission ratio model, which predicts the load transmission ratio based on collected data. Calculate the decay threshold curve and transmission ratio failure threshold curve The load transmission ratio Multiplying these values ​​by the transmission ratio threshold coefficient and the failure coefficient respectively yields the degradation threshold curve. and transmission ratio failure threshold curve ;

[0008] Step 2: Confirm the vehicle's task information and read the current vehicle transmission ratio model;

[0009] Step 3: Read the steering subsystem operating information and the actual operating gear ratio of the steering subsystem. ;

[0010] Step four: Determine whether the transmission subsystem is operating normally according to the predetermined degradation judgment strategy. If it is operating normally, repeat steps two, three, and four until the task is completed. If it is not operating normally, issue a system warning and recalibrate the transmission subsystem.

[0011] Furthermore, the transmission ratio model is established based on SVR and ANFIS algorithms. The ANFIS fuzzy neural network structure in the transmission ratio model has a total of 5 layers. The input is the real-time motion state of the vehicle, including vehicle speed, yaw rate, steering wheel angle and wheel speed. The first 4 layers are used to match the antecedent of the fuzzy rules, and the 5th layer is used to generate the consequent of the fuzzy rules. The input modulus of the model is 4, and the number of fuzzy segments of the input is 3.

[0012] Furthermore, the transmission ratio is trained and predicted using the LIBSVM library, and the transmission ratio uses a radial basis kernel function.

[0013] Furthermore, the steering subsystem operating information read in step three is preprocessed, specifically including:

[0014] Data sample at the location The, the The first sample The indicators are Then the average value of each indicator and standard deviation for:

[0015] ;

[0016] ;

[0017] The original data is standardized as follows:

[0018] ;

[0019] in, represent Standardized data.

[0020] Furthermore, the transmission ratio threshold coefficient is a preset constant.

[0021] Furthermore, the predetermined decline judgment strategy described in step four specifically includes:

[0022] when At that time, the steering subsystem gear ratio is in a normal state;

[0023] when At this time, the transmission ratio needs to be recalibrated;

[0024] when At that time, the steering subsystem recalibration strategy is executed.

[0025] Furthermore, the transmission ratio threshold coefficient for:

[0026] ;

[0027] in, This refers to the net load transmission ratio of the steering subsystem obtained at a specified mileage. The net load transmission ratio of the steering subsystem. This is the initial mileage transmission ratio threshold.

[0028] Furthermore, the predetermined decline judgment strategy described in step four specifically includes:

[0029] When the transmission ratio threshold coefficient If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated.

[0030] When the transmission ratio threshold coefficient and If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated.

[0031] When the transmission ratio threshold coefficient and and At that time, the transmission subsystem was recalibrated;

[0032] In other cases, the transmission subsystem is considered to be operating normally.

[0033] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0034] The method proposed in this application uses an adaptive neuro-fuzzy system and support vector regression to establish a model between the transmission ratio and steering parameters. It can adaptively adjust the transmission ratio threshold according to the actual operating state without having to reset the threshold parameters for each angle, thus adapting to changes in multiple operating environments.

[0035] This application calculates the theoretical load transmission ratio using a model and updates the transmission ratio threshold in real time. This solves the problem of difficulty in synchronizing the transmission ratio threshold in real time due to changes in load and vehicle speed, thereby reducing false alarms and effectively monitoring the operating status of the steering subsystem.

[0036] After establishing the model, this application only requires setting an initial threshold coefficient to achieve adaptive monitoring, which greatly simplifies the complexity and workload of setting the threshold and reduces costs. Simultaneously, this method enables software development on the onboard computing platform of the unmanned mining truck, collecting internal signals without modifying the truck. It integrates the steering calibration strategy into the unmanned driving system, achieving real-time and accurate monitoring of the steering subsystem, thus improving the operational safety and efficiency of the unmanned mining truck. Attached Figure Description

[0037] Figure 1 The training and monitoring process of the transmission ratio model provided in the embodiments of the present invention;

[0038] Figure 2 This is a flowchart of the steering subsystem status monitoring provided in an embodiment of the present invention. Detailed Implementation

[0039] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Before describing the technical solutions of each embodiment of the present invention in detail, the terms and terms involved will be explained. In this specification, components with the same name or the same reference numerals represent similar or the same structures and are limited to illustrative purposes.

[0040] This invention primarily studies the online monitoring problem of the steering subsystem of unmanned mining trucks. Based on the transmission ratio threshold method, a transmission ratio model is established to describe the relationship between the operating parameters of the steering subsystem and the transmission ratio, displaying the real-time motion status of the vehicle. This includes the relationship between vehicle speed, yaw rate, steering wheel angle, and transmission ratio signal, solving the problem of current transmission ratio calibration strategies for the steering subsystem of unmanned mining trucks. After establishing the transmission ratio model, adaptive monitoring can be achieved by simply setting an initial threshold coefficient. This method can be developed on the onboard computing platform of the unmanned mining truck, collecting internal signals without modifying the truck. The steering calibration strategy is integrated into the unmanned driving system, and a recalibration strategy is immediately executed when the transmission ratio failure condition of the steering subsystem is met, providing the unmanned mining truck with the correct steering strategy before affecting its safe operation.

[0041] While the driverless mining truck is operating, the fault monitoring system reads relevant data and uses the transmission ratio model to calculate the standard load transmission ratio. Transmission ratio threshold: decay threshold curve and transmission ratio failure threshold curve .

[0042] The transmission ratio model is established using SVR and ANFIS algorithms and updated periodically to improve accuracy under different operating mileages. The SVR model has a fast training speed and can be trained and updated online. The ANFIS model has higher accuracy but a longer training time; however, it consumes more system resources and can be updated during non-operating periods of the mining truck or on a cloud server. The load transmission ratio under standard conditions is calculated using SVR and ANFIS. and steering subsystem operating mileage threshold curve , .

[0043] The transmission ratio model is trained and predicted using the LIBSVM library, and the radial basis function kernel can be selected. The ANFIS fuzzy neural network structure in the transmission ratio model has five layers, with the real-time vehicle motion state as input, including vehicle speed, yaw rate, steering wheel angle, and wheel speed. The first four layers are used to match the antecedents of the fuzzy rules, and the fifth layer is used to generate the consequents of the fuzzy rules; the model input modulus is 4, and the number of fuzzy segments in the input is 3. After establishing and training the ANFIS model, the output ANFIS model result graph is used to represent the mapping relationship between yaw rate and transmission ratio at different vehicle speeds.

[0044] Model construction based on SVR and ANFIS algorithms is common knowledge in the field, and will not be elaborated upon in this invention.

[0045] When the driverless mining truck starts operating, parameter settings are first required, including reading in relevant parameters, setting the transmission ratio threshold coefficient, and accessing historical operating information. Because the input parameters of the monitoring system vary significantly in magnitude, the input data needs to be standardized. Data preprocessing can improve the model's computation speed and error accuracy. The data sample here is... The, the The first sample The indicators are Then the average value of each indicator and standard deviation for:

[0046] ;

[0047] ;

[0048] Therefore, the original data can be standardized as follows:

[0049] ;

[0050] Using standardized data, load parameter-transmission ratio models based on SVR and ANFIS are established respectively. Since the models are built using standardized data, the solution results need to be de-standardized to obtain the standard load transmission ratio.

[0051] For a newly deployed type of unmanned mining truck, a transmission ratio model for this type of unmanned mining truck needs to be established through training. The training and monitoring processes are as follows. Figure 1 Show.

[0052] During the monitoring process, based on the actual measured transmission ratio The performance of the steering system is evaluated within the threshold range. When the actual transmission ratio exceeds the threshold curve for a certain period of time, the steering subsystem is determined to have entered the recalibration phase, and the corresponding recalibration strategy is executed.

[0053] The degradation judgment strategy for the transmission ratio model is as follows, where The actual operating gear ratio of the steering subsystem currently being monitored:

[0054] (1) When At this time, the steering subsystem gear ratio is in the normal range, meeting safety requirements;

[0055] (2) When At that time, the steering subsystem's transmission ratio was in a stage with large errors, which had already affected driving safety, and the transmission ratio needed to be recalibrated;

[0056] (3) When At that time, the steering subsystem transmission ratio was in a stage of serious error, which could not guarantee the driving safety of the unmanned mining truck, and the system executed the steering subsystem recalibration strategy.

[0057] The above strategies are based on constant thresholds. While the advantage of constant threshold methods lies in their simplicity, the determination of the threshold coefficient lacks a set principle, exhibiting significant subjectivity and arbitrariness, and has a limited applicability, making it prone to monitoring threshold failure. This invention addresses the inconsistencies arising from changes in operating conditions by proposing a real-time threshold update monitoring strategy. In the calculation of the unmanned mining truck transmission ratio threshold, a transmission ratio threshold coefficient function is introduced to adapt to the updated transmission ratio model.

[0058] ;

[0059] in, This is the transmission ratio threshold coefficient. This refers to the net load transmission ratio of the steering subsystem obtained at a specific mileage. The net load transmission ratio of the steering subsystem. This is the initial mileage transmission ratio threshold.

[0060] Load transmission ratio It can be represented as:

[0061] ;

[0062] in, The load transmission ratio is calculated using a real-time threshold update strategy. The average load transmission ratio of a certain vehicle. The transmission load ratio of the transmission system at a specific operating mileage. is the transmission coefficient.

[0063] Will Multiplying these values ​​by the transmission ratio threshold coefficient and the failure coefficient respectively yields the degradation threshold curve. and transmission ratio failure threshold curve :

[0064] ;

[0065] ;

[0066] in, The load transmission ratio is calculated using a real-time threshold update strategy. This represents the failure factor.

[0067] Introducing a transmission ratio threshold coefficient Subsequently, the method flow provided by this invention is as follows: Figure 2 As shown: First, confirm the vehicle's task information and read the current vehicle transmission ratio model; then, read the subsystem's operating information and update the transmission ratio model periodically; calculate the standard load transmission ratio. and coefficient, The coefficient is the transmission ratio threshold coefficient. And implement the following strategy:

[0068] (1) When the transmission ratio threshold coefficient If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated.

[0069] (2) When the transmission ratio threshold coefficient and If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated.

[0070] (3) When the transmission ratio threshold coefficient and and At that time, the transmission subsystem was recalibrated;

[0071] (4) In other cases, the transmission subsystem is judged to be operating normally.

[0072] After completing one task, check if all tasks are completed. If not, repeat the above steps until all tasks are completed.

[0073] The above-described embodiments are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal, characterized in that, Includes the following steps: Step 1: Construct a transmission ratio model, which predicts the load transmission ratio based on collected data. Calculate the decay threshold curve and transmission ratio failure threshold curve The load transmission ratio Multiplying these values ​​by the transmission ratio threshold coefficient and the failure coefficient respectively yields the degradation threshold curve. and transmission ratio failure threshold curve ; Step 2: Confirm the vehicle's task information and read the current vehicle transmission ratio model; Step 3: Read the steering subsystem operating information and the actual operating gear ratio of the steering subsystem. ; Step four: Determine whether the transmission subsystem is operating normally according to the predetermined degradation judgment strategy. If it is operating normally, repeat steps two, three, and four until the task is completed. If it is not operating normally, issue a system warning and recalibrate the transmission subsystem.

2. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 1, characterized in that, The transmission ratio model is based on the SVR and ANFIS algorithms. The ANFIS fuzzy neural network structure in the transmission ratio model has a total of 5 layers. The input is the real-time motion state of the vehicle, including vehicle speed, yaw rate, steering wheel angle and wheel speed. The first 4 layers are used to match the antecedent of the fuzzy rules, and the 5th layer is used to generate the consequent of the fuzzy rules. The input modulus of the model is 4, and the number of fuzzy segments of the input is 3.

3. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 1, characterized in that, The transmission ratio is trained and predicted using the LIBSVM library, and the transmission ratio uses the radial basis kernel function.

4. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 1, characterized in that, The steering subsystem operating information read in step three is preprocessed, specifically including: Data sample is The, the The first sample The indicators are Then the average value of each indicator and standard deviation for: ； ； The original data is standardized as follows: ； in, represent Standardized data.

5. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 1, characterized in that, The transmission ratio threshold coefficient is a preset constant.

6. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 5, characterized in that, The predetermined decline judgment strategy described in step four specifically includes: when At that time, the steering subsystem gear ratio is in a normal state; when At this time, the transmission ratio needs to be recalibrated; when At that time, the steering subsystem recalibration strategy is executed.

7. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 1, characterized in that, Transmission ratio threshold coefficient for: ； in, This refers to the net load transmission ratio of the steering subsystem obtained at a specified mileage. The net load transmission ratio of the steering subsystem. This is the initial mileage transmission ratio threshold.

8. The monitoring method for the steering system of an unmanned mining truck based on a transmission ratio signal according to claim 7, characterized in that, The predetermined decline judgment strategy described in step four specifically includes: When the transmission ratio threshold coefficient If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated. When the transmission ratio threshold coefficient and If this occurs, a system warning will be sent, and the transmission subsystem will be recalibrated. When the transmission ratio threshold coefficient and and At that time, the transmission subsystem was recalibrated; In other cases, the transmission subsystem is considered to be operating normally.

Images