Intelligent fault detection system for methanol engine

Abstract

The invention discloses a methanol engine fault intelligent detection system, and relates to the field of engine fault detection, and the system comprises a vehicle speed monitoring module which is used for monitoring the vehicle speed information in real time, and carrying out the storage of the vehicle speed information; the detection module is used for collecting infrared thermal imaging images and vibration signals of a vehicle engine in real time and storing the infrared thermal imaging images and the vibration signals; according to the method, infrared thermal imaging and vibration signals are fused, the engine state is comprehensively and accurately detected, more representative detection data can be screened out under complex working conditions through comprehensive consideration of information in multiple aspects such as the vehicle speed and vehicle balance, the detection accuracy is greatly improved, and in the fault risk analysis link, the fault risk analysis efficiency is greatly improved. The reference value and the risk value are calculated by using a unique algorithm, and the weight coefficient is intelligently adjusted according to the vehicle speed, so that the fault risk assessment better fits the actual situation.

Description

Technical Field

[0001] The present invention relates to the technical field of engine fault detection, and in particular to an intelligent fault detection system for a methanol engine. Background Art

[0002] Methanol engines offer certain advantages in the automotive sector. They burn cleanly, reducing harmful emissions, are widely available, and are relatively inexpensive. Furthermore, they offer superior power performance, comparable to traditional gasoline engines, and have already been widely adopted in some regions.

[0003] The invention patent application with application number 202010574693.0 discloses a method for detecting methanol engine failure, including: real-time collection of the rotational speed of the methanol engine; when the rotational speed of the methanol engine is less than or equal to a first preset value, collecting the oil emulsification value of the methanol engine; when the rotational speed of the methanol engine is greater than or equal to a second preset value, collecting the gas pressure value of the oil pan space of the methanol engine; judging whether the oil in the methanol engine is emulsified based on the oil emulsification value or the oil pan space gas pressure value; if so, controlling the methanol engine to act accordingly according to the degree of emulsification; the emulsification degree includes primary emulsification and secondary emulsification: and the step of controlling the methanol engine to act accordingly according to the emulsification degree includes: judging whether the emulsification degree is primary emulsification or secondary emulsification; if the emulsification degree is the primary emulsification, controlling the methanol engine to operate within a preset power range; if the emulsification degree is the secondary emulsification, controlling the methanol engine to stop working. This application aims to solve the problem of how to detect oil emulsification early and thus prevent methanol engine failure.

[0004] However, when methanol engines are used in automotive power components, the probability of failure during operation may change at any time depending on the operation of the vehicle driver, which also makes it difficult for conventional related fault detection technologies to be well compatible with fault detection during vehicle operation.

[0005] Therefore, an intelligent fault detection system for methanol engines is proposed. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides a methanol engine fault intelligent detection system, which can effectively solve the problems of the prior art.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention discloses an intelligent methanol engine fault detection system, comprising: a vehicle speed monitoring module, for monitoring vehicle speed information in real time, and storing the vehicle speed information; a detection module, for collecting infrared thermal imaging images and vibration signals of the vehicle engine in real time, and storing the infrared thermal imaging images and vibration signals; an analysis module, for acquiring infrared thermal imaging images and vibration signals in the monitoring module, and analyzing the methanol engine fault risk based on the infrared thermal imaging images and vibration information; a determination module, for setting a methanol engine fault determination threshold, receiving a methanol engine fault risk determination result in the analysis module, and determining whether the methanol engine has a fault based on a comparison between the determination result and the engine fault determination threshold; and a prediction module, for traversing historical methanol engine fault analysis results of the analysis module, and predicting whether the methanol engine has a fault tendency based on the traversal of the analysis results.

[0008] Furthermore, a sensing unit is provided inside the vehicle speed monitoring module, and the sensing unit is used to sense the vehicle balance information in real time, store the balance information, and determine in real time whether the vehicle is currently on a flat road. The operating frequency of the sensing unit is the same as that of the vehicle speed monitoring module; Among them, each time the perception unit senses the vehicle balance information, it synchronously determines whether the vehicle is currently on a flat road. The perception unit is integrated with four laser ranging sensors, which are recorded as the upper left, lower left, upper right, and lower right laser ranging sensors based on the top-down plane perspective. The four laser ranging sensors operate synchronously, and the distance information sensed by the operation is the vehicle balance information sensed by the perception unit.

[0009] Furthermore, the perception unit is stacked and deployed on the surface of the vehicle chassis, and the ranging target is the distance between the vehicle itself and the road surface. The judgment logic of whether the vehicle is on a flat road in the perception unit is expressed as follows: ; Where: is the judgment value; Deployment volume of laser ranging sensors; is the ranging result of the i-th laser ranging sensor and the i+1-th laser ranging sensor; is a preset ranging error threshold for determining vehicle tilt; is the decision function; Among them, the decision function The value is subject to: If established, =1, If not established, =0, calculated based on formula (1), the judgment value is When formula (2) holds true, the vehicle is determined to be on a level road; otherwise, the vehicle is determined to be not on a level road.

[0010] Furthermore, the detection module performs a storage operation phase to distinguish and store the collected infrared thermal imaging image and the vibration signal; The monitoring module executes the vehicle engine infrared thermal imaging image and vibration signal acquisition stage, and simultaneously obtains the judgment result of whether the vehicle is on a level road in the vehicle speed monitoring module. In the time domain when the judgment result is yes, the vehicle engine infrared thermal imaging image and vibration signal acquisition operation is performed. Based on the acquisition time domain of the vehicle engine infrared thermal imaging image and vibration signal, the vehicle speed information monitored by the vehicle speed monitoring module in the corresponding time domain is synchronously acquired. The complexity of the vehicle operating condition is analyzed based on the vehicle speed information. The commercial vehicle engine infrared thermal imaging image and vibration signal are screened from the collected vehicle engine infrared thermal imaging image and vibration signal according to the vehicle operating condition complexity analysis result.

[0011] Furthermore, the vehicle operating condition complexity analysis logic is expressed as: Sorting vehicle speed information based on time sequence, and performing vehicle operating condition complexity analysis with every three adjacent vehicle speed information as a group; ; Where: The complexity of vehicle working conditions; is the speed of the qth and q+1th vehicles; The angles between the qth and q+1th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis, and the angles between the q+1th and q+2th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis; in, The larger it is, the more complex the vehicle operating condition is. The vehicle speed information is stored in the form of a line graph. The horizontal axis of the line graph represents time and the vertical axis represents vehicle speed. The system user defines a threshold for determining the complexity of the vehicle operating condition. The vehicle operating condition complexity calculation result based on each group of vehicle speed information is compared with the threshold for determining the complexity of the vehicle operating condition to determine the vehicle speed information with complex vehicle operating conditions. The vehicle engine infrared thermal imaging image and vibration signal belonging to the vehicle speed information other than the corresponding vehicle speed information with a determination result of complex vehicle operating conditions are recorded as the screening result of the infrared thermal imaging image and vibration signal of the commercial vehicle engine.

[0012] Furthermore, the infrared thermal imaging image and vibration signal acquired by the analysis module are the infrared thermal imaging image and vibration signal of the commercial vehicle engine obtained by screening; The analysis module is provided with a classification unit and a recording unit at the lower level. The classification unit is used to classify the infrared thermal imaging images and vibration signals, and simultaneously reclassify them according to the vehicle speed information of the infrared thermal imaging images and vibration signals. The infrared thermal imaging images or vibration signals corresponding to the same vehicle speed information are classified into one category. The recording unit is used to record the methanol engine failure risk analysis results of each operation of the analysis module.

[0013] Furthermore, the methanol engine failure risk analysis logic in the analysis module is expressed as: ; Where: is the reference value for methanol engine failure risk; is the total amount of infrared thermal imaging images; is the difference between the jth infrared thermal imaging image and the j+1th infrared thermal imaging image; The total amount of spectrum representing the vibration signal; is the difference between the spectrum of the vth segment and the spectrum of the v+1th segment; The risk of methanol engine failure; is the total amount of the reference value for methanol engine failure risk; is the weight coefficient; Among them, the vibration signal is expressed in the form of spectrum. Based on a set of infrared thermal imaging images and a set of vibration signals, and the infrared thermal imaging images and vibration signals correspond to the same vehicle speed information, the methanol engine failure risk reference value is obtained based on the infrared thermal imaging images and vibration signals corresponding to the same vehicle speed information, and the methanol engine failure risk reference value set is obtained, that is, , and finally obtain , The larger the value, the higher the risk of methanol engine failure.

[0014] Furthermore, the Calculation is performed based on the color distribution difference algorithm, Calculation is based on the Euclidean distance algorithm; The weight coefficient obey , and each weight coefficient is a positive number, and the weight coefficient is The calculation formula also follows the setting logic that the faster the vehicle speed corresponding to the weight coefficient product object is, the larger the weight coefficient value is.

[0015] Furthermore, the prediction module is triggered to run when the determination module has determined that the result is negative for three consecutive times: The prediction module obtains the three latest methanol engine failure risk analysis results analyzed by the analysis module in the recording unit. If the three latest methanol engine failure analysis results show a continuous upward trend, it is predicted that the methanol engine has a failure tendency; otherwise, it does not have a failure tendency.

[0016] Furthermore, the vehicle speed monitoring module is electrically connected to a perception unit through a medium, the vehicle speed monitoring module is interactively connected to a detection module through a wireless network, the detection module is interactively connected to an analysis module through a wireless network, the analysis module is interactively connected to a classification unit and a recording unit through a wireless network, and the analysis module is interactively connected to a determination module and a prediction module through a wireless network.

[0017] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: The present invention provides an intelligent methanol engine fault detection system. During operation, the system integrates infrared thermal imaging and vibration signals to comprehensively and accurately detect engine status. By comprehensively considering multiple aspects of information such as vehicle speed and balance, it can filter out more representative detection data under complex operating conditions, significantly improving detection accuracy. In the fault risk analysis phase, a unique algorithm is used to calculate reference values ​​and risk values, and the weight coefficient is intelligently adjusted based on vehicle speed, making the fault risk assessment more accurate. In addition, the system can not only determine whether there is an engine fault in real time, but also predict the fault tendency based on historical analysis results when it is determined to be fault-free for many consecutive times, providing a scientific basis for maintenance in advance, effectively reducing the losses caused by engine failure, and ensuring the safe and stable operation of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0019] Figure 1 This is a structural diagram of an intelligent detection system for methanol engine faults. DETAILED DESCRIPTION

[0020] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] The present invention will be further described below with reference to the embodiments.

[0022] Example: A methanol engine fault intelligent detection system of this embodiment is as follows Figure 1 Shown, including: The vehicle speed monitoring module is used to monitor the vehicle speed information in real time and store the vehicle speed information; It should be noted that when monitoring vehicle speed information, the vehicle speed information is monitored through contact or non-contact: Contact type: measurement through physical connection, such as wheel speed sensor, drive shaft speed sensor, odometer flexible shaft.

[0023] Non-contact: No physical contact is required, such as GPS / Beidou, lidar, millimeter-wave radar, and visual sensors. Traffic monitoring can also use differential Doppler radar for long-distance speed measurement.

[0024] The speed monitoring module is equipped with a sensing unit, which is used to sense the vehicle balance information in real time, store the balance information, and determine whether the vehicle is currently on a flat road in real time. The sensing unit and the speed monitoring module operate at the same frequency. Each time the perception unit senses vehicle balance information, it simultaneously determines whether the vehicle is currently on a flat road. The perception unit is integrated with four laser ranging sensors, which are denoted as the upper left, lower left, upper right, and lower right laser ranging sensors based on a bird's-eye view. The four laser ranging sensors operate synchronously, and the distance information sensed by the operation is the vehicle balance information sensed by the perception unit. The perception unit is stacked and deployed on the surface of the vehicle chassis. The distance measurement target is the distance between the vehicle itself and the road surface. The judgment logic of whether the vehicle is on a flat road in the perception unit is expressed as follows: ; Where: is the judgment value; Deployment volume of laser ranging sensors; is the ranging result of the i-th laser ranging sensor and the i+1-th laser ranging sensor; is a preset ranging error threshold for determining vehicle tilt; is the decision function; Among them, the decision function The value is subject to: If established, =1, If not established, =0, calculated based on formula (1), the judgment value is When the equation (2) holds true, the vehicle is judged to be on a level road; otherwise, the vehicle is judged to be not on a level road. By calculating through the above logic formula, it is determined whether the vehicle is on a flat road, thereby providing support for the subsequent screening of thermal imaging images and vibration signals in this embodiment.

[0025] A detection module is used to collect infrared thermal imaging images and vibration signals of vehicle engines in real time and store them; It should be noted that the vehicle engine infrared thermal imaging image and vibration signal are collected by the following means: Infrared thermal imaging image acquisition: Primarily utilizing infrared thermal imagers, these cameras are categorized into portable handheld devices and vehicle-mounted fixed systems. Portable devices are used by a user to scan various engine components, capturing surface temperature distribution and generating thermal images. These are suitable for maintenance and inspection scenarios. Vehicle-mounted fixed systems, on the other hand, utilize infrared cameras integrated into the vehicle or inspection equipment to capture real-time thermal images of the engine during operation. Combined with data processing software, these systems analyze areas of temperature anomalies. These are commonly used in automated inspection lines or on-board intelligent diagnostic systems.

[0026] Vibration signal acquisition: Vibration sensors are installed magnetically, bolted, or adhesively to vibration-sensitive areas such as the engine block, crankcase, and bearing housing to detect acceleration, velocity, or displacement signals generated by mechanical vibration in real time. The sensors convert the vibration signals into electrical signals, which are then converted to digital by a data collector and transmitted via wired or wireless transmission to analysis equipment. Algorithms such as spectrum analysis and time-frequency analysis are used to extract vibration characteristics and identify faults such as engine wear, looseness, and imbalance. These two types of signals are often used in combination to enhance the accuracy of engine condition monitoring through multi-source data fusion.

[0027] The detection module performs the storage operation phase, distinguishing and storing the collected infrared thermal imaging images and vibration signals; The monitoring module executes the vehicle engine infrared thermal imaging image and vibration signal acquisition phase, and simultaneously obtains the determination result of the vehicle speed monitoring module on whether the vehicle is on a level road. In the time domain when the determination result is yes, the monitoring module performs the vehicle engine infrared thermal imaging image and vibration signal acquisition operation. Based on the acquisition time domain of the vehicle engine infrared thermal imaging image and vibration signal, the monitoring module synchronously acquires the vehicle speed information monitored by the speed monitoring module in the corresponding time domain. The complexity of the vehicle operating condition is analyzed based on the vehicle speed information. The commercial vehicle engine infrared thermal imaging image and vibration signal are screened from the acquired vehicle engine infrared thermal imaging image and vibration signal according to the vehicle operating condition complexity analysis result. The logic of vehicle operating condition complexity analysis is expressed as: Sorting vehicle speed information based on time sequence, and performing vehicle operating condition complexity analysis with every three adjacent vehicle speed information as a group; ; Where: The complexity of vehicle working conditions; is the speed of the qth and q+1th vehicles; The angles between the qth and q+1th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis, and the angles between the q+1th and q+2th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis; in, The larger the value, the more complex the vehicle operating condition. The vehicle speed information is stored in the form of a broken line graph, with the horizontal axis of the broken line graph representing time and the vertical axis representing vehicle speed. The system user defines a threshold for determining vehicle operating condition complexity. The vehicle operating condition complexity calculation result based on each group of vehicle speed information is compared with the threshold for determining vehicle operating condition complexity to determine vehicle speed information with complex vehicle operating conditions. The infrared thermal imaging images and vibration signals of the vehicle engines belonging to the vehicle speed information other than the corresponding vehicle speed information with a determination result of complex vehicle operating conditions are recorded as the screening results of the infrared thermal imaging images and vibration signals of the commercial vehicle engines. The complexity of the vehicle operating conditions is calculated through the above logical formula, which can be used as support for further screening of thermal imaging images and vibration signals, and more valuable thermal imaging images and vibration signal data can be selected to support the fault detection accuracy of methanol engines.

[0028] An analysis module is used to obtain infrared thermal imaging images and vibration signals in the monitoring module and analyze the failure risk of the methanol engine based on the infrared thermal imaging images and vibration information; The infrared thermal imaging image and vibration signal acquired by the analysis module are the available vehicle engine infrared thermal imaging image and vibration signal obtained by screening; The analysis module is equipped with a classification unit and a recording unit at the lower level. The classification unit is used to classify the infrared thermal imaging images and vibration signals, and simultaneously reclassify them based on the vehicle speed information of the infrared thermal imaging images and vibration signals. Vehicles with the same speed information are classified into the same category corresponding to the infrared thermal imaging images or vibration signals. The recording unit is used to record the methanol engine fault risk analysis results of each run of the analysis module. The methanol engine failure risk analysis logic in the analysis module is expressed as: ; Where: is the reference value for methanol engine failure risk; is the total amount of infrared thermal imaging images; is the difference between the jth infrared thermal imaging image and the j+1th infrared thermal imaging image; The total amount of spectrum representing the vibration signal; is the difference between the spectrum of the vth segment and the spectrum of the v+1th segment; The risk of methanol engine failure; is the total amount of the reference value for methanol engine failure risk; is the weight coefficient; Among them, the vibration signal is expressed in the form of spectrum. Based on a set of infrared thermal imaging images and a set of vibration signals, and the infrared thermal imaging images and vibration signals correspond to the same vehicle speed information, the methanol engine failure risk reference value is obtained based on the infrared thermal imaging images and vibration signals corresponding to the same vehicle speed information, and the methanol engine failure risk reference value set is obtained, that is, , and finally obtain , The larger the value, the higher the risk of methanol engine failure; Calculation is based on the color distribution difference algorithm. Calculation is based on the Euclidean distance algorithm; The above logic formula provides a specific judgment logic for the methanol engine fault judgment of the system in this embodiment; Weight coefficient obey , and each weight coefficient is a positive number, and the weight coefficient is The calculation formula also follows the setting logic that the faster the vehicle speed corresponding to the weight coefficient product object is, the larger the weight coefficient value is; a determination module, configured to set a methanol engine fault determination threshold, receive the methanol engine fault risk determination result from the analysis module, and determine whether the methanol engine has a fault based on a comparison of the determination result with the engine fault determination threshold; The prediction module is used to traverse the historical methanol engine fault analysis results of the analysis module and predict whether the methanol engine has a fault tendency based on the traversal of the analysis results; The prediction module is triggered to run when the judgment module's latest three consecutive judgment results are negative: The prediction module obtains the three most recent methanol engine failure risk analysis results analyzed by the analysis module from the recording unit. If the three most recent methanol engine failure analysis results show a continuous upward trend, it is predicted that the methanol engine has a failure tendency; otherwise, it does not have a failure tendency. The vehicle speed monitoring module is electrically connected to a perception unit through a medium, the vehicle speed monitoring module is interactively connected to a detection module through a wireless network, the detection module is interactively connected to an analysis module through a wireless network, the analysis module is interactively connected to a classification unit and a recording unit through a wireless network, and the analysis module is interactively connected to a judgment module and a prediction module through a wireless network.

[0029] In this embodiment, the vehicle speed monitoring module monitors vehicle speed information in real time. Based on the storage of the vehicle speed information, the sensing unit simultaneously senses vehicle balance information in real time, stores the balance information, and determines in real time whether the vehicle is currently on a level road. The detection module operates in a post-processing manner to collect infrared thermal imaging images and vibration signals of the vehicle engine in real time and stores the infrared thermal imaging images and vibration signals. The analysis module further obtains the infrared thermal imaging images and vibration signals from the monitoring module and analyzes the methanol engine failure risk based on the infrared thermal imaging images and vibration information. The classification unit simultaneously classifies the infrared thermal imaging images and vibration signals and simultaneously reclassifies them based on the vehicle speed information from which the infrared thermal imaging images and vibration signals originate, so that infrared thermal imaging images or vibration signals corresponding to the same vehicle speed information are classified into the same category. The recording unit records the methanol engine failure risk analysis results of each run of the analysis module in real time. The determination module sets a methanol engine failure determination threshold, receives the methanol engine failure risk determination result from the analysis module, and determines whether the methanol engine has a failure based on the comparison of the determination result with the engine failure determination threshold. Finally, the prediction module traverses the historical methanol engine failure analysis results of the analysis module and, based on the traversal of the analysis results, predicts whether the methanol engine has a failure tendency.

[0030] The system in the above embodiment performs fault detection on the methanol engine in the vehicle power unit, and provides real-time fault determination and fault prediction for the operation process of the methanol engine in a compatible manner, thereby effectively ensuring the safety and reliability of the operation of the methanol engine.

[0031] In addition, the detection system's speed monitoring module includes a built-in perception unit consisting of four laser ranging sensors symmetrically positioned on the vehicle chassis. These sensors measure the distance to the road in real time to determine whether the vehicle is on a level road. The judgment logic is as follows: if the difference in distance between adjacent sensors is less than or equal to a preset threshold, the judgment function determines that the vehicle is on a level road when the judgment value P = 3 (i.e., any three adjacent sensors meet the condition), providing a stable road condition basis for detection data collection.

[0032] The detection module collects engine infrared thermal imaging and vibration signals only during flat road conditions, and simultaneously acquires vehicle speed information in the corresponding time domain. The system analyzes the complexity of operating conditions by speed time series, calculating a line graph based on the angle difference between three adjacent speed data segments. The greater the difference in angle between segments, the more complex the operating condition. A user-defined threshold is used to filter out signal data from simple operating conditions, which is then classified and stored as valid detection data.

[0033] The analysis module performs fault risk analysis on the filtered signal data. It calculates adjacent differences in infrared thermal imaging image sequences and vibration signal spectrum sequences at the same vehicle speed using a color distribution difference algorithm and a Euclidean distance algorithm, respectively. This generates a single-condition fault risk reference value. Multi-condition risk values ​​are calculated using a weighted summation, where the weight coefficients sum to 1 and increase with vehicle speed. The prediction module is triggered when the judgment module determines there are no faults three times in a row. If the three most recent fault risk values ​​show a continuous upward trend, a fault tendency is predicted. Each module exchanges data via a wireless network, forming a closed-loop detection system.

[0034] In summary, during operation, the system in the above embodiment integrates infrared thermal imaging and vibration signals to comprehensively and accurately detect the engine status. By comprehensively considering various information such as vehicle speed and vehicle balance, it can screen out more representative detection data under complex working conditions, greatly improving the accuracy of detection. In the fault risk analysis link, a unique algorithm is used to calculate the reference value and risk value, and the weight coefficient is intelligently adjusted according to the vehicle speed to make the fault risk assessment more in line with the actual situation. In addition, the system can not only determine whether there is a fault in the engine in real time, but also predict the fault tendency based on historical analysis results when it is determined to be fault-free for many consecutive times, providing a scientific basis for maintenance in advance, effectively reducing the losses caused by engine failure, and ensuring the safe and stable operation of the vehicle.

[0035] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A methanol engine fault intelligent detection system, characterized in that: include: The vehicle speed monitoring module is used to monitor the vehicle speed information in real time and store the vehicle speed information; A detection module is used to collect infrared thermal imaging images and vibration signals of vehicle engines in real time and store them; An analysis module is used to obtain infrared thermal imaging images and vibration signals in the monitoring module and analyze the failure risk of the methanol engine based on the infrared thermal imaging images and vibration information; a determination module, configured to set a methanol engine fault determination threshold, receive the methanol engine fault risk determination result from the analysis module, and determine whether the methanol engine has a fault based on a comparison of the determination result with the engine fault determination threshold; The prediction module is used to traverse the historical methanol engine fault analysis results of the analysis module and predict whether the methanol engine has a fault tendency based on the traversal of the analysis results.

2. The intelligent methanol engine fault detection system according to claim 1, characterized in that: The vehicle speed monitoring module is internally provided with a sensing unit, which is used to sense the vehicle balance information in real time, store the balance information, and determine in real time whether the vehicle is currently on a flat road. The sensing unit and the vehicle speed monitoring module operate at the same frequency; Among them, each time the perception unit senses the vehicle balance information, it synchronously determines whether the vehicle is currently on a flat road. The perception unit is integrated with four laser ranging sensors, which are recorded as the upper left, lower left, upper right, and lower right laser ranging sensors based on the top-down plane perspective. The four laser ranging sensors operate synchronously, and the distance information sensed by the operation is the vehicle balance information sensed by the perception unit.

3. The intelligent methanol engine fault detection system according to claim 2, characterized in that: The perception unit is stacked and deployed on the surface of the vehicle chassis. The distance measurement target is the distance between the vehicle itself and the road surface. The judgment logic of whether the vehicle is on a flat road in the perception unit is expressed as follows: ； Where: is the judgment value; Deployment volume of laser ranging sensors; is the ranging result of the i-th laser ranging sensor and the i+1-th laser ranging sensor; is a preset ranging error threshold for determining vehicle tilt; is the decision function; Among them, the decision function The value is subject to: If established, =1, If not established, =0, calculated based on formula (1), the judgment value is When formula (2) holds true, the vehicle is determined to be on a level road; otherwise, the vehicle is determined to be not on a level road.

4. The intelligent methanol engine fault detection system according to claim 1, characterized in that: The detection module performs a storage operation phase to distinguish and store the collected infrared thermal imaging images and vibration signals; The monitoring module executes the vehicle engine infrared thermal imaging image and vibration signal acquisition stage, and simultaneously obtains the judgment result of whether the vehicle is on a level road in the vehicle speed monitoring module. In the time domain when the judgment result is yes, the vehicle engine infrared thermal imaging image and vibration signal acquisition operation is performed. Based on the acquisition time domain of the vehicle engine infrared thermal imaging image and vibration signal, the vehicle speed information monitored by the vehicle speed monitoring module in the corresponding time domain is synchronously acquired. The complexity of the vehicle operating condition is analyzed based on the vehicle speed information. The commercial vehicle engine infrared thermal imaging image and vibration signal are screened from the collected vehicle engine infrared thermal imaging image and vibration signal according to the vehicle operating condition complexity analysis result.

5. The intelligent fault detection system for a methanol engine according to claim 4, characterized in that: The vehicle operating condition complexity analysis logic is expressed as: Sorting vehicle speed information based on time sequence, and performing vehicle operating condition complexity analysis with every three adjacent vehicle speed information as a group; ； Where: The complexity of vehicle working conditions; is the speed of the qth and q+1th vehicles; The angles between the qth and q+1th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis, and the angles between the q+1th and q+2th vehicle speed representation line segments in the vehicle speed information line graph and the horizontal axis; in, The larger it is, the more complex the vehicle operating condition is. The vehicle speed information is stored in the form of a line graph. The horizontal axis of the line graph represents time and the vertical axis represents vehicle speed. The system user defines a threshold for determining the complexity of the vehicle operating condition. The vehicle operating condition complexity calculation result based on each group of vehicle speed information is compared with the threshold for determining the complexity of the vehicle operating condition to determine the vehicle speed information with complex vehicle operating conditions. The vehicle engine infrared thermal imaging image and vibration signal belonging to the vehicle speed information other than the corresponding vehicle speed information with a determination result of complex vehicle operating conditions are recorded as the screening result of the infrared thermal imaging image and vibration signal of the commercial vehicle engine.

6. The intelligent methanol engine fault detection system according to claim 1, characterized in that: The infrared thermal imaging image and vibration signal acquired by the analysis module are the infrared thermal imaging image and vibration signal of the commercial vehicle engine obtained by screening; The analysis module is provided with a classification unit and a recording unit at the lower level. The classification unit is used to classify the infrared thermal imaging images and vibration signals, and simultaneously reclassify them according to the vehicle speed information of the infrared thermal imaging images and vibration signals. The infrared thermal imaging images or vibration signals corresponding to the same vehicle speed information are classified into one category. The recording unit is used to record the methanol engine failure risk analysis results of each operation of the analysis module.

7. The intelligent methanol engine fault detection system according to claim 6, characterized in that: The methanol engine failure risk analysis logic in the analysis module is expressed as follows: ； Where: is the reference value for methanol engine failure risk; is the total amount of infrared thermal imaging images; is the difference between the jth infrared thermal imaging image and the j+1th infrared thermal imaging image; The total amount of spectrum representing the vibration signal; is the difference between the spectrum of the vth segment and the spectrum of the v+1th segment; The risk of methanol engine failure; is the total amount of the reference value for methanol engine failure risk; is the weight coefficient; Among them, the vibration signal is expressed in the form of spectrum. Based on a set of infrared thermal imaging images and a set of vibration signals, and the infrared thermal imaging images and vibration signals correspond to the same vehicle speed information, the methanol engine failure risk reference value is obtained based on the infrared thermal imaging images and vibration signals corresponding to the same vehicle speed information, and the methanol engine failure risk reference value set is obtained, that is, , and finally obtain , The larger the value, the higher the risk of methanol engine failure.

8. The intelligent methanol engine fault detection system according to claim 7, characterized in that: described Calculation is performed based on the color distribution difference algorithm, Calculation is based on the Euclidean distance algorithm; The weight coefficient obey , and each weight coefficient is a positive number, and the weight coefficient is The calculation formula also follows the setting logic that the faster the vehicle speed corresponding to the weight coefficient product object is, the larger the weight coefficient value is.

9. The intelligent methanol engine fault detection system according to claim 1, characterized in that: The prediction module is triggered to run when the judgment module's latest three consecutive judgment results are negative: The prediction module obtains the three latest methanol engine failure risk analysis results analyzed by the analysis module in the recording unit. If the three latest methanol engine failure analysis results show a continuous upward trend, it is predicted that the methanol engine has a failure tendency; otherwise, it does not have a failure tendency.

10. The intelligent fault detection system for a methanol engine according to claim 1, characterized in that: The vehicle speed monitoring module is electrically connected to a perception unit through a medium, the vehicle speed monitoring module is interactively connected to a detection module through a wireless network, the detection module is interactively connected to an analysis module through a wireless network, the analysis module is interactively connected to a classification unit and a recording unit through a wireless network, and the analysis module is interactively connected to a determination module and a prediction module through a wireless network.

Images