Electric locomotive auxiliary driving system based on artificial intelligence

Abstract

The invention relates to the technical field of mine transportation, and particularly discloses an electric locomotive auxiliary driving system based on artificial intelligence. Comprising an auxiliary driving analysis index monitoring module, an ARM edge computer, an electric locomotive operation state analysis module, a transportation environment state analysis module, an electric locomotive adaptability adjustment module, a driving behavior evaluation module, an auxiliary driving strategy optimization module, an electric locomotive operation early warning module and a ground monitoring center. Collected data are transmitted to each analysis module in real time through an ARM edge computer to be analyzed and processed, and corresponding fault early warning and electric locomotive auxiliary driving regulation and control are carried out according to an analysis and processing result, so that the safety of the electric locomotive during transportation of operating personnel in a gate way is ensured; dangerous driving early warning signals are sent to drivers on the electric locomotive and a ground monitoring center in time, and safe and efficient operation of the electric locomotive is further guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of mine transportation, and specifically refers to an auxiliary driving system for electric locomotives based on artificial intelligence. Background Art

[0002] In the level transportation scenario of industries such as mines, electric locomotives are important transportation tools, and the safety and efficiency of their operation are crucial.

[0003] Currently, the traditional driving of electric locomotives mainly relies on the experience and operation of drivers, lacking a comprehensive and accurate monitoring and intelligent auxiliary system. On the one hand, for the monitoring of the operation status of electric locomotives, single-index analysis or simple threshold judgment methods are mostly used, which are difficult to comprehensively capture the potential fault risks of electric locomotives under complex working conditions, and are prone to misjudgment or missed judgment, resulting in the inability to detect and handle faults in a timely manner, and further causing problems such as transportation interruption and equipment damage, affecting the production progress and increasing the maintenance cost. On the other hand, in terms of transportation environment monitoring, the existing technologies often cannot evaluate in real time and accurately the influence of environmental factors such as gas concentration, dust content, track flatness, and water accumulation on the operation of electric locomotives, and also lack effective coping strategies for different environmental abnormal conditions, making there are great safety hazards when electric locomotives operate in harsh environments. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the existing technology, the present invention provides an auxiliary driving system for electric locomotives based on artificial intelligence to solve the above-mentioned technical defects.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An auxiliary driving system for electric locomotives based on artificial intelligence includes an auxiliary driving analysis index monitoring module, an ARM edge computer, an electric locomotive operation status analysis module, a transportation environment status analysis module, an electric locomotive adaptability adjustment module, a driving behavior evaluation module, an auxiliary driving strategy optimization module, an electric locomotive operation warning module, and a ground monitoring center; the auxiliary driving analysis index monitoring module establishes a wireless communication connection with the electric locomotive operation status analysis module, the transportation environment status analysis module, and the driving behavior evaluation module through the ARM edge computer; the transportation environment status analysis module is connected to the electric locomotive adaptability adjustment module; the driving behavior evaluation module is connected to the auxiliary driving strategy optimization module; the electric locomotive operation status analysis module, the electric locomotive adaptability adjustment module, and the auxiliary driving strategy optimization module are all connected to the electric locomotive operation warning module; the electric locomotive operation warning module is wirelessly communicatively connected to the ground monitoring center through the ARM edge computer.

[0006] Further, the assisted driving analysis index monitoring module uses various sensors to monitor, collect, and process the locomotive operation parameters, transportation environment parameters, driver operation data, and driver driving behavior parameters according to their respective set monitoring and collection frequencies. After that, the assisted driving analysis indexes are aligned in chronological order, and the least common multiple of the sampling frequencies of each sensor is used to unify the sampling frequency. Then, the data is transmitted to each analysis module in real time through the ARM edge computer.

[0007] Further, the locomotive operation parameters include locomotive speed, acceleration, steering angle, motor working temperature, and remaining battery power; the level transportation environment parameters include gas concentration, dust content, track water accumulation status, and height difference of each section of the track; the driver operation data includes the depression depth of the accelerator pedal, the depression depth of the brake pedal, and the steering angle of the steering wheel.

[0008] Further, the locomotive operation status analysis module conducts fault prediction and analysis based on the locomotive operation indexes. Specifically, it obtains the operation index data of the locomotive at each monitoring moment in each monitoring period during operation, calculates the mean and standard deviation of each operation index respectively, takes the sum of the mean and twice the standard deviation as the maximum value of the normal range of each operation index, and the difference between the mean and twice the standard deviation as the minimum value to form the normal range of each operation index. Then, it compares the real-time operation index data with the normal range, generates corresponding fault signals according to different situations, and combines them into a locomotive operation anomaly signal.

[0009] Further, the transportation environment status analysis module conducts environmental assessment and analysis based on the environmental indexes during the locomotive operation. It sets the gas concentration safety threshold and dust content safety threshold according to the safety production manual, sets the track flatness threshold according to the safety regulations of the locomotive operation track, and generates corresponding signals and combines them into a transportation environment anomaly signal through the monitoring and analysis of environmental indexes such as gas concentration, dust content, track height difference, and water accumulation status, and sends it to the locomotive adaptability adjustment module.

[0010] Further, the locomotive adaptability adjustment module analyzes the transportation environment anomaly signal generated by the transportation environment status analysis module. When receiving different anomaly signals, it calculates the comparison value of the gas concentration, the comparison value of the track flatness, or the difference result between the water accumulation depth and the tire radius respectively, establishes a deceleration coefficient relationship table based on these results to obtain the deceleration coefficient, multiplies the current locomotive speed by the deceleration coefficient to get the adjusted speed, and then obtains the locomotive adaptability adjustment strategy.

[0011] Further, the driving behavior evaluation module establishes a driving behavior evaluation model based on the driver's operations on the accelerator pedal, brake pedal, and steering wheel, obtains the pedal depression depth and steering wheel rotation angle at the current moment, calculates the change rate of pedal operation within a time interval, determines sudden acceleration, sudden braking, and dangerous steering behaviors based on the thresholds specified by the normal operation parameters of the battery locomotive, and calculates the comprehensive driving behavior score by combining the weights set according to historical data.

[0012] Further, the assisted driving strategy optimization module optimizes and adjusts the assisted driving strategy parameters according to the comprehensive driving behavior score calculated by the driving behavior evaluation module. When detecting unsafe driving behaviors, it feeds back to the driver through the display screen and voice prompt of the battery locomotive; if the comprehensive driving behavior score is lower than the set threshold, it automatically reduces the upper limit of the power output of the battery locomotive and restricts the maximum effect of the accelerator pedal.

[0013] Further, the battery locomotive operation warning module is used to receive the monitoring abnormal signals of the battery locomotive operation and the driver, and is communicatively connected to the display screen on the battery locomotive to perform acoustic and optical warnings in the way of popping up the corresponding abnormal information box, the display screen flashing red light and emitting a continuous harsh alarm sound, so as to ensure the safe operation of the battery locomotive and the life safety of the driver.

[0014] Further, the ground monitoring center is used to dynamically display various assisted driving analysis indicators of the battery locomotive, and at the same time receive the monitoring abnormal signals of the battery locomotive operation and the driver, and take the same acoustic and optical warning measures as the battery locomotive operation warning module to ensure the safe operation of the battery locomotive and the life safety of the driver.

[0015] Advantages of the present invention:

[0016] 1. The assisted driving analysis index monitoring module monitors and collects various parameters of the battery locomotive's operation parameters, the environmental parameters of the roadway transportation, the operation data of the driver on the battery locomotive, and the driving behavior parameters of the driver when driving the battery locomotive respectively through various sensors according to their respective set monitoring and acquisition frequencies; the ARM edge computer transmits the collected data to each analysis module in real time for analysis and processing, and performs corresponding fault warnings and assisted driving regulation of the battery locomotive according to the analysis and processing results, so as to ensure the safety of transporting operating personnel inside the roadway by the battery locomotive. Finally, combined with the analysis of the driving behavior of the battery locomotive driver based on artificial intelligence, the driving behavior of the driver is monitored in real time. When it is determined that the driving behavior of the driver is abnormal, a dangerous driving warning signal is sent to the driver on the battery locomotive and the ground monitoring center in a timely manner, further ensuring the safe and efficient operation of the battery locomotive.

[0017] 2. In terms of the comprehensiveness of fault prediction, the present invention comprehensively considers multiple operating indicators such as the speed, acceleration, steering angle, motor operating temperature, and remaining battery power of the electric locomotive, avoiding the limitations of relying solely on a single indicator analysis, and being able to capture potential fault risks during the operation of the electric locomotive more comprehensively. From the perspective of accuracy, the normal range is determined by calculating the mean and standard deviation of each indicator parameter, making the judgment standard more in line with the actual operating characteristics of the electric locomotive. Moreover, when analyzing, the correlation relationships between multiple indicators are combined. For example, when the speed is abnormal, indicators such as acceleration and motor temperature are correlated; when the acceleration is abnormal, the steering angle, motor temperature, etc. are considered, greatly improving the accuracy of fault judgment and effectively reducing misjudgment situations. In terms of the timeliness of fault warning, once it is found that the operating indicators exceed the normal range or the correlation between indicators appears abnormal, corresponding fault signals can be quickly generated, which helps the staff to promptly know the abnormal conditions of the electric locomotive, so as to quickly take measures to ensure the safe and stable operation of the electric locomotive, reduce the risks of transportation interruption and equipment damage caused by faults, and thus improve the overall transportation efficiency and economic benefits.

[0018] 3. From the aspect of safety guarantee in the present invention, the thresholds of key environmental indicators such as gas concentration, dust content, and track flatness are set according to the safety production manual and track safety regulations, providing scientific and strict standards for the safety assessment of the electric locomotive operation environment; by real-time monitoring these indicators, once the gas concentration or dust content exceeds the standard, or the track flatness or water accumulation situation appears abnormal, corresponding danger or abnormal signals can be quickly generated, timely discovering potential safety hazards, greatly reducing the risk of accidents caused by environmental problems, and ensuring the safety of personnel and equipment during the operation of the electric locomotive; in terms of improving the operation efficiency, the generated abnormal signals of the transportation environment are promptly sent to the electric locomotive adaptive adjustment module, enabling the electric locomotive to quickly make adaptive adjustments according to environmental changes, avoiding operation failures or stagnations caused by environmental discomfort, ensuring the continuity of transportation work, and thus effectively improving the overall transportation efficiency and reducing the operation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below with reference to the drawings.

[0020] Figure 1 is the principle block diagram of the electric locomotive auxiliary driving system based on artificial intelligence according to the embodiment of the present invention;

[0021] Figure 2 is the logic flow chart for comparative analysis of the operating states of the electric locomotive according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0023] Embodiment 1

[0024] Please refer to Figure 1 As shown, the artificial intelligence-based auxiliary driving system for a battery locomotive includes: an auxiliary driving analysis index monitoring module, an ARM edge computer, a battery locomotive operation state analysis module, a transportation environment state analysis module, a battery locomotive adaptability adjustment module, a driving behavior evaluation module, an auxiliary driving strategy optimization module, a battery locomotive operation warning module, and a ground monitoring center; the auxiliary driving analysis index monitoring module is wirelessly communicatively connected to the battery locomotive operation state analysis module, the transportation environment state analysis module, and the driving behavior evaluation module respectively through the ARM edge computer, the transportation environment state analysis module is connected to the battery locomotive adaptability adjustment module, the driving behavior evaluation module is connected to the auxiliary driving strategy optimization module, the battery locomotive operation state analysis module, the battery locomotive adaptability adjustment module, and the auxiliary driving strategy optimization module are all connected to the battery locomotive operation warning module, and the battery locomotive operation warning module is wirelessly communicatively connected to the ground monitoring center through the ARM edge computer.

[0025] Specifically, the auxiliary driving analysis index monitoring module monitors and collects various parameters of the battery locomotive's operation parameters, roadway transportation environment parameters, the driver's operation data of the battery locomotive, and the driver's driving behavior parameters during driving the battery locomotive through various sensors according to their respective set monitoring and acquisition frequencies; the ARM edge computer transmits the collected data to each analysis module in real time for analysis and processing, and performs corresponding fault warnings and auxiliary driving regulation of the battery locomotive according to the analysis and processing results, so as to ensure the safety of transporting operating personnel inside the roadway by the battery locomotive. Finally, based on artificial intelligence, the driving behavior of the battery locomotive driver is analyzed, the driving behavior of the driver is monitored in real time, and when it is determined that the driver has abnormal driving behavior, a dangerous driving warning signal is sent to the driver on the battery locomotive and the ground monitoring center in a timely manner to further ensure the safe and efficient operation of the battery locomotive.

[0026] It should be further noted that the auxiliary driving analysis index monitoring module monitors and obtains the auxiliary driving analysis indexes through the sensors corresponding to each index, aligns each auxiliary driving analysis index in chronological order, and then unifies the sampling frequency by taking the least common multiple of the sampling frequencies of each sensor.

[0027] Specifically, the auxiliary driving analysis indicators include, but are not limited to: the locomotive speed collected by the speed sensor, the locomotive acceleration collected by the acceleration sensor, the locomotive steering angle measured by the steering angle sensor, the working temperature of the motor monitored by the motor temperature sensor, the remaining battery power obtained by the battery power sensor, the gas concentration in the mine collected by the gas sensor, the dust content obtained by the dust sensor, the track water accumulation state detected by the water accumulation sensor, the height difference of each section of the track calculated by the track flatness detection sensor, the depression depth of the accelerator pedal, the depression depth of the brake pedal, and the steering angle of the steering wheel obtained by the sensor.

[0028] It should be further noted that the locomotive operation status analysis module performs fault prediction analysis based on the operation indicators during the operation of the locomotive, and obtains the fault prediction signal during the operation of the locomotive.

[0029] Among them, the operation indicators during the operation of the locomotive include the locomotive speed, locomotive acceleration, locomotive steering angle, motor working temperature, and remaining battery power during the operation of the locomotive.

[0030] Specifically, the method for performing fault prediction analysis based on the operation indicators during the operation of the locomotive is as follows:

[0031] Obtain the locomotive speed, locomotive acceleration, locomotive steering angle, motor working temperature, and remaining battery power at each monitoring moment in each monitoring period during the operation of the locomotive, calculate the mean and standard deviation of each operation index parameter of the locomotive respectively, use the sum of the mean and twice the standard deviation of each operation index of the locomotive as the maximum value of the normal range of each operation index, use the difference between the mean and twice the standard deviation of each operation index of the locomotive as the minimum value of the normal range of each operation index, and form the normal range of each operation index of the locomotive through the maximum value of the normal range of each operation index and the minimum value of the normal range of each operation index.

[0032] The locomotive operation parameters include locomotive speed, acceleration, steering angle, motor working temperature, and remaining battery power; the roadway transportation environment parameters include gas concentration, dust content, track water accumulation state, and the height difference of each section of the track; the driver operation data includes the depression depth of the accelerator pedal, the depression depth of the brake pedal, and the steering angle of the steering wheel.

[0033] As Figure 2 shown, compare and analyze the locomotive speed and the normal range of locomotive speed at each monitoring moment in each monitoring period during the operation of the locomotive. The specific analysis process is as follows:

[0034] When the locomotive speed at each monitoring moment during each monitoring period when the locomotive is in operation is not within the normal range of the locomotive speed, 1) At this time, if the absolute value of the difference between the locomotive acceleration and the average acceleration is greater than twice the acceleration standard deviation, it indicates that there is an abnormality in the locomotive power system, and a "speed & power system fault signal" is generated; 2) At this time, if the motor operating temperature is greater than the sum of the motor operating temperature and twice the motor operating temperature standard deviation, it indicates that the motor operating temperature is abnormal, and a "speed & motor overload fault signal" is generated.

[0035] When the locomotive acceleration at each monitoring moment during each monitoring period when the locomotive is in operation is not within the normal range of the locomotive acceleration, 1) When turning, if the absolute value change of the steering angle does not match the acceleration, it indicates that there is an abnormality in the locomotive steering system, and an "acceleration & steering system abnormality signal" is generated; 2) At this time, if the motor operating temperature is greater than the sum of the motor operating temperature and twice the motor operating temperature standard deviation, it indicates that the motor operating temperature is abnormal, and an "acceleration & motor overload fault signal" is generated.

[0036] When the motor operating temperature at each monitoring moment during each monitoring period when the locomotive is in operation is not within the normal range of the motor operating temperature, and the decline rate of the remaining battery power exceeds the normal decline rate range, it indicates that the battery output is unstable, and a "motor temperature & battery output abnormality" is generated; among them, the normal decline rate range of the battery power is obtained through calculation and analysis of a large amount of historical normal operation data.

[0037] The "speed & power system fault signal", "speed & motor overload fault signal", "acceleration & steering system abnormality signal", "acceleration & motor overload fault signal" and "motor temperature & battery output abnormality" are combined together to form a locomotive operation abnormality signal.

[0038] Specifically, in terms of the comprehensiveness of fault prediction, the present invention comprehensively considers multiple operating indicators such as the locomotive speed, acceleration, steering angle, motor operating temperature, and remaining battery power, avoiding the limitations of relying solely on single-index analysis, and being able to more comprehensively capture potential fault risks during the operation of the locomotive. From the perspective of accuracy, the normal range is determined by calculating the mean and standard deviation of each index parameter, making the judgment standard more in line with the actual operating characteristics of the locomotive. Moreover, when analyzing, the correlation relationships between multiple indicators are combined. For example, when the speed is abnormal, indicators such as acceleration and motor temperature are associated; when the acceleration is abnormal, the steering angle, motor temperature, etc. are considered, greatly improving the accuracy of fault judgment and effectively reducing misjudgment situations. In terms of the timeliness of fault warning, once it is found that the operating indicators exceed the normal range or the correlation between indicators appears abnormal, corresponding fault signals can be quickly generated, which helps the staff to promptly know the abnormal conditions of the locomotive, so as to quickly take measures to ensure the safe and stable operation of the locomotive, reduce the risks of transportation interruption and equipment damage caused by faults, and thus improve the overall transportation efficiency and economic benefits.

[0039] It should be further noted that the transportation environment state analysis module conducts environmental assessment and analysis based on the environmental indicators of the locomotive during operation to obtain the environmental state signals of the locomotive during operation.

[0040] Among them, the environmental indicators of the locomotive during operation include gas concentration, dust content, track water accumulation status, and the height difference of each section of the track.

[0041] Specifically, the method of conducting environmental assessment and analysis based on the environmental indicators of the locomotive during operation is as follows:

[0042] Set the safety thresholds for gas concentration and dust content underground according to the safety production manual, and set the track flatness threshold according to the safety regulations of the locomotive's operating track.

[0043] When the gas concentration at each monitoring moment in each monitoring period during the operation of the locomotive exceeds the set safety threshold for gas concentration, it indicates that the gas concentration reaches a dangerous level, and a "dangerous gas concentration signal" is generated.

[0044] When the dust content at each monitoring moment in each monitoring period during the operation of the locomotive exceeds the set safety threshold for dust content, it indicates that the dust content is too high, and a "dangerous dust content signal" is generated.

[0045] Calculate the mean and standard deviation of the height difference of each section of the track underground. When the mean or standard deviation of the track height difference exceeds the set track flatness threshold, it indicates that the track flatness is poor, and an "abnormal operating track signal" is generated.

[0046] For the track area determined to be in a water accumulation state and the duration exceeds the set reasonable time, it indicates that there is a continuous water accumulation problem in this track area, and an "abnormal signal of track water accumulation" is generated.

[0047] Combine the above-generated "dangerous signal of gas concentration", "dangerous signal of dust content", "abnormal signal of running track", and "abnormal signal of track water accumulation" into an abnormal signal of the transportation environment, and send the abnormal signal of the transportation environment to the locomotive adaptability adjustment module for locomotive adaptability adjustment analysis.

[0048] In a specific embodiment, from the perspective of safety guarantee in the present invention, the thresholds of key environmental indicators such as gas concentration, dust content, and track flatness are set according to the safety production manual and track safety regulations, providing a scientific and strict standard for the safety assessment of the locomotive operation environment; by real-time monitoring these indicators, once the gas concentration or dust content exceeds the standard, or the track flatness or water accumulation situation is abnormal, corresponding dangerous or abnormal signals can be quickly generated, potential safety hazards can be discovered in time, greatly reducing the risk of accidents caused by environmental problems and ensuring the safety of personnel and equipment during the locomotive operation; in terms of improving the operation efficiency, the generated abnormal signal of the transportation environment is sent to the locomotive adaptability adjustment module in time, enabling the locomotive to quickly make adaptability adjustments according to environmental changes, avoiding operation failures or stagnations caused by environmental discomfort, ensuring the continuity of transportation work, and thus effectively improving the overall transportation efficiency and reducing the operation cost.

[0049] It should be further explained that the locomotive adaptability adjustment module analyzes based on the abnormal signal of the transportation environment generated in the transportation environment state analysis module to obtain the locomotive adaptability adjustment strategy.

[0050] The specific method of analyzing based on the abnormal signal of the transportation environment generated in the transportation environment state analysis module is as follows:

[0051] When receiving the "dangerous signal of gas concentration" or "dangerous signal of dust content", calculate the difference result between the gas concentration and the gas concentration safety threshold, calculate the ratio of the difference result to the gas concentration safety threshold to obtain the gas concentration benchmark value, establish a deceleration coefficient relationship table according to the gas concentration benchmark value, and obtain the corresponding deceleration coefficient through the deceleration coefficient relationship table; specifically, if the gas concentration benchmark value is between 0 and 0.5, the deceleration coefficient is taken as 0.8 at this time, if the gas concentration benchmark value is between 0.5 and 1, the deceleration coefficient is taken as 0.6 at this time, if the gas concentration benchmark value is greater than 1, the deceleration coefficient is taken as 0.4 at this time, and multiply the current locomotive speed by the deceleration coefficient to obtain the adjusted locomotive speed.

[0052] When receiving the "abnormal running track signal", calculate the difference result between the average value of the track height difference and the track flatness threshold, calculate the ratio of the difference result to the track flatness threshold to obtain the track flatness comparison value, establish a deceleration coefficient relationship table based on the track flatness comparison value, and obtain the corresponding deceleration coefficient through the deceleration coefficient relationship table; specifically, if the track flatness comparison value is between 0 and 0.2, the deceleration coefficient is taken as 0.85 at this time. If the track flatness comparison value is between 0.2 and 0.5, the deceleration coefficient is taken as 0.7 at this time. If the track flatness comparison value is greater than 0.5, the deceleration coefficient is taken as 0.5 at this time. Multiply the current locomotive speed by the deceleration coefficient to obtain the adjusted locomotive speed.

[0053] When receiving the "abnormal track water accumulation signal", calculate the difference result between the water accumulation depth and the tire radius, establish a deceleration coefficient relationship table based on the difference result, and obtain the corresponding deceleration coefficient through the deceleration coefficient relationship table; specifically, if the difference result is less than 1 / 4, the deceleration coefficient is taken as 0.8 at this time. If the difference result is between 1 / 4 and 1 / 2, the deceleration coefficient is taken as 0.6 at this time. If the track flatness comparison value is greater than 1 / 2, the deceleration coefficient is taken as 0.4 at this time. Multiply the current locomotive speed by the deceleration coefficient to obtain the adjusted locomotive speed.

[0054] In a specific embodiment, in terms of safety, for different abnormal signals in the transportation environment, such as gas concentration danger, dust content danger, abnormal running track, and abnormal track water accumulation, etc., detailed and reasonable deceleration strategies are formulated respectively. Quantitative calculations are carried out according to the severity of each abnormal situation, such as gas concentration comparison value, track flatness comparison value, difference result between water accumulation depth and tire radius, etc., and a deceleration coefficient relationship table is established accordingly, so that the locomotive can accurately adjust the speed according to the environmental risk level, effectively reducing the possibility of accidents when driving in a dangerous environment, and providing a reliable safety guarantee for the operation of the locomotive; in terms of adaptability, this method of differential adjustment according to the specific environmental abnormalities can enable the locomotive to better cope with the complex and changeable underground transportation environment, avoid vehicle damage or operation failures caused by environmental factors, ensure the stable operation of the locomotive in various abnormal environments, and thus ensure the smooth progress of the transportation task and improve the reliability and stability of the overall transportation system.

[0055] It should be further noted that the driving behavior evaluation module establishes a driving behavior evaluation model based on the operations of the locomotive driver on the accelerator pedal, brake pedal, and steering wheel, and calculates the comprehensive driving behavior score in combination with the calculation results and weights of various indicators.

[0056] The specific calculation and analysis method of the comprehensive driving behavior score is as follows:

[0057] Obtain the depression depths of the accelerator pedal and the brake pedal at the current moment. The value ranges of both are [0, 1], where 0 indicates not depressed and 1 indicates fully depressed. The sampling frequency is f. At the same time, obtain the rotation angle of the steering wheel.

[0058] Obtain the depression depths of the accelerator pedal and the brake pedal with a time interval of t. By subtracting the depression depth of the accelerator pedal at the current moment from the depression depth of the accelerator pedal with a time interval of t, and dividing the result of the subtraction calculation by the time interval t, the change rate of the accelerator pedal operation is obtained. Similarly, the change rate of the brake pedal operation is calculated; where the time interval t = 1 / f.

[0059] According to the normal operation parameters of the battery locomotive, obtain the rapid acceleration threshold, rapid braking threshold, and dangerous steering angle change threshold of the battery locomotive. When the change rate of the accelerator pedal operation is greater than the rapid acceleration threshold, it is recorded as one rapid acceleration. When the change rate of the brake pedal operation is greater than the rapid braking threshold, it is recorded as one rapid braking. When the difference between the rotation angle of the steering wheel at this moment and the rotation angle of the steering wheel with a time interval of t is calculated, and the absolute value of the difference calculation result is greater than the dangerous steering angle change threshold, it is recorded as one dangerous steering. According to the summary of a large amount of historical data, set the weight values of the rapid braking operation score, rapid acceleration operation score, and dangerous steering operation score, and perform product calculations and summations with the rapid braking operation score, rapid acceleration operation score, and dangerous steering operation score respectively to obtain the comprehensive driving behavior score.

[0060] It should be further noted that the auxiliary driving strategy optimization module optimizes and adjusts the auxiliary driving strategy parameters according to the comprehensive driving behavior score calculated in the driving behavior evaluation module.

[0061] The specific method for optimizing and adjusting the auxiliary driving strategy parameters is as follows:

[0062] When detecting unsafe driving behaviors such as rapid acceleration, rapid braking, or dangerous steering, the system gives real-time feedback to the driver through the battery locomotive display screen and voice prompts, such as "Please accelerate smoothly", "Avoid rapid braking", etc.

[0063] If the comprehensive driving behavior score is lower than the set comprehensive driving behavior score threshold, the system automatically reduces the upper limit of the power output of the battery locomotive, limits the maximum effect of the accelerator pedal, and multiplies the original power output upper limit by (1 minus the adjustment coefficient determined according to the severity of the unsafe behavior) to obtain the optimized and adjusted upper limit value of the battery locomotive power output.

[0064] It should be noted that the comprehensive driving behavior score threshold is dynamically set manually based on statistical analysis of historical data. When the operating state and environmental state of the battery locomotive are good, the comprehensive driving behavior score threshold can be appropriately increased.

[0065] In a specific embodiment, in the evaluation of driving behavior, the present invention accurately calculates the pedal operation change rate by obtaining the real-time depression depths of the accelerator pedal and the brake pedal and the rotation angle of the steering wheel, determines the behaviors of sudden acceleration, sudden braking and dangerous steering according to the established thresholds, and obtains the comprehensive driving behavior score by combining the weights set according to historical data, so as to comprehensively and objectively evaluate the operation behavior of the driver; in terms of optimizing the assisted driving strategy, when detecting unsafe driving behaviors, it timely gives real-time feedback to the driver through the display screen and voice prompts, which helps to guide the driver to develop good driving habits; if the comprehensive driving behavior score is lower than the threshold, the system automatically reduces the upper limit of the power output of the battery locomotive, restricts the effect of the accelerator pedal, and reduces the risks brought by unsafe driving from the hardware level; in addition, the threshold of the comprehensive driving behavior score can be dynamically adjusted according to the operating state and environment of the battery locomotive, making the evaluation and optimization strategies more flexible and adaptable, thereby effectively improving the safety and stability of the battery locomotive operation and reducing the probability of failures and accidents.

[0066] It should be further noted that the battery locomotive operation warning module is used to receive the monitoring abnormal signals of the battery locomotive operation and the battery locomotive driver and take corresponding measures for audible and visual warnings to ensure the operation safety of the battery locomotive and the life safety of the driver.

[0067] Specifically, the battery locomotive operation warning module is communicatively connected to the display screen provided on the battery locomotive. When the battery locomotive operation warning module receives the "motor temperature & battery output abnormal" in the battery locomotive operation abnormal signal, an information box of "motor temperature & battery output abnormal" is popped up through the display screen on the battery locomotive, and at the same time, the display screen of the battery locomotive continuously flashes red light and emits a continuous harsh alarm sound; replacing the "motor temperature & battery output abnormal" in the battery locomotive operation abnormal signal with others, the warning method only changes the text content in the information box, and other warning methods remain unchanged.

[0068] It should be further noted that the ground monitoring center is used to dynamically display various assisted driving analysis indicators of the battery locomotive, and at the same time receive the monitoring abnormal signals of the battery locomotive operation and the battery locomotive driver and take corresponding measures for audible and visual warnings to ensure the operation safety of the battery locomotive and the life safety of the driver.

[0069] In addition, those skilled in the art can understand that various aspects of the present invention can be illustrated and described by several patentable types or situations, including any new and useful processes, machines, products, or combinations of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present invention can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". In addition, various aspects of the present invention may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0070] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense, unless expressly so defined herein.

[0071] The above is the description of the present invention and should not be regarded as a limitation thereof. Although several exemplary embodiments of the present invention have been described, those skilled in the art will easily understand that many modifications can be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined by the claims. It should be understood that the above is the description of the present invention and should not be considered limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. An electric locomotive assisted driving system based on artificial intelligence, comprising an assisted driving analysis index monitoring module, an ARM edge computer, an electric locomotive operation status analysis module, a transportation environment status analysis module, an electric locomotive adaptability adjustment module, a driving behavior evaluation module, an assisted driving strategy optimization module, an electric locomotive operation warning module and a ground monitoring center; characterized in that, The assisted driving analysis index monitoring module establishes a wireless communication connection with the electric locomotive operation status analysis module, the transportation environment status analysis module and the driving behavior evaluation module with the help of the ARM edge computer; the transportation environment status analysis module is connected to the electric locomotive adaptability adjustment module; the driving behavior evaluation module is connected to the assisted driving strategy optimization module; the electric locomotive operation status analysis module, the electric locomotive adaptability adjustment module and the assisted driving strategy optimization module are all connected to the electric locomotive operation warning module; the electric locomotive operation warning module is wirelessly connected to the ground monitoring center through the ARM edge computer.

2. The electric locomotive assisted driving system based on artificial intelligence according to claim 1 is characterized in that: The assisted driving analysis index monitoring module uses various sensors to monitor and collect the electric locomotive operating parameters, transportation environment parameters, driver operation data and driver driving behavior parameters according to their respective set monitoring and collection frequencies. After that, the various assisted driving analysis indicators are aligned in chronological order, and the lowest common multiple of the sampling frequencies of each sensor is taken to unify the sampling frequencies. The data is then transmitted to each analysis module in real time through the ARM edge computer.

3. The electric locomotive assisted driving system based on artificial intelligence according to claim 2 is characterized in that: The locomotive operating parameters include the locomotive speed, acceleration, steering angle, motor operating temperature and battery remaining power; the level tunnel transportation environment parameters include gas concentration, dust content, track water accumulation status and the height difference of each track section; the driver operation data includes the accelerator pedal's depression depth, the brake pedal's depression depth and the steering angle of the steering wheel.

4. The electric locomotive assisted driving system based on artificial intelligence according to claim 3 is characterized in that: The electric locomotive operation status analysis module performs fault prediction analysis based on the electric locomotive operation indicators. Specifically, the operation indicator data of the electric locomotive at each monitoring time in each monitoring period during the operation process are obtained, and the mean and standard deviation of each operation indicator are calculated respectively. The sum of the mean and twice the standard deviation is used as the maximum value of the normal range of each operation indicator, and the difference between the mean and twice the standard deviation is used as the minimum value to form the normal range of each operation indicator. The real-time operation indicator data is then compared with the normal range, and corresponding fault signals are generated according to different situations, and combined into an abnormal operation signal of the electric locomotive.

5. The electric locomotive assisted driving system based on artificial intelligence according to claim 4 is characterized in that: The transport environment status analysis module performs environmental assessment and analysis based on environmental indicators during the operation of the electric locomotive, sets gas concentration safety thresholds and dust content safety thresholds according to the safety production manual, sets track flatness thresholds according to the safety regulations for the electric locomotive running tracks, and generates corresponding signals through monitoring and analysis of environmental indicators such as gas concentration, dust content, track height difference and water accumulation status, and combines them into transport environment abnormality signals, which are sent to the electric locomotive adaptability adjustment module.

6. The electric locomotive assisted driving system based on artificial intelligence according to claim 5 is characterized in that: The electric locomotive adaptive adjustment module analyzes the transport environment abnormal signal generated by the transport environment status analysis module. When different abnormal signals are received, the gas concentration benchmark value, the track flatness benchmark value or the difference between the water depth and the tire radius are calculated respectively. Based on these results, a deceleration coefficient relationship table is established to obtain the deceleration coefficient. The adjusted speed is obtained by multiplying the current electric locomotive speed by the deceleration coefficient, and then the adaptive adjustment strategy of the electric locomotive is obtained.

7. The electric locomotive assisted driving system based on artificial intelligence according to claim 6 is characterized in that: The driving behavior evaluation module establishes a driving behavior evaluation model based on the driver's operation of the accelerator pedal, brake pedal and steering wheel, obtains the pedal depression depth and steering wheel rotation angle at the current moment, calculates the pedal operation change rate within the time interval, judges sudden acceleration, sudden braking and dangerous steering behaviors according to the threshold value specified by the normal operating parameters of the electric locomotive, and calculates the comprehensive driving behavior score based on the weight set by historical data.

8. The electric locomotive assisted driving system based on artificial intelligence according to claim 7 is characterized in that: The assisted driving strategy optimization module optimizes and adjusts the assisted driving strategy parameters according to the comprehensive driving behavior score calculated by the driving behavior evaluation module, and when unsafe driving behavior is detected, feedback is given to the driver through the electric locomotive display screen and voice prompts; If the comprehensive driving behavior score is lower than the set threshold, the upper limit of the electric vehicle power output will be automatically lowered to limit the maximum effect of the accelerator pedal.

9. The electric locomotive assisted driving system based on artificial intelligence according to claim 8 is characterized in that: The electric locomotive operation warning module is used to receive monitoring abnormal signals of the electric locomotive operation and the driver, and is connected to the display screen on the electric locomotive to provide an audible and visual warning by popping up a corresponding abnormal information box, flashing a red light on the display screen, and emitting a continuous piercing alarm sound, so as to ensure the safety of the electric locomotive operation and the life of the driver.

10. The electric locomotive assisted driving system based on artificial intelligence according to claim 9 is characterized in that: The ground monitoring center is used to dynamically display various auxiliary driving analysis indicators of the electric locomotive, receive monitoring abnormal signals of the electric locomotive operation and the driver, and take the same sound and light warning measures as the electric locomotive operation warning module to ensure the safe operation of the electric locomotive and the life safety of the driver.

Images