Air spring system operation monitoring method and related equipment

Abstract

The invention discloses an air spring system operation monitoring method and related equipment, and belongs to the technical field of vehicle air springs. The method comprises the steps that pressure information and height information of an air spring system and air pump working time are obtained, time sequence feature extraction is conducted, and the pressure change rate, the height sensor standard deviation and the air pump working period proportion are determined; the pressure change rate, the height sensor standard deviation and the air pump work period proportion are processed through a trained isolated random forest algorithm, the abnormal score of the air pump is obtained, and a leakage mark is determined; and the real-time temperature, the real-time pressure and the real-time height of the air spring system are obtained, the real-time temperature, the real-time pressure, the real-time height and the abnormal score and the leakage mark of the air pump are compared with preset rules, and the fault early warning level and the corresponding solution are determined. The reliability of operation monitoring of the air spring system can be improved, and the problem that potential faults of the air spring system cannot be warned in advance in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle air springs, and in particular, to a method for monitoring the operation of an air spring system and related equipment. Background Technique

[0002] The statements in this part only mention the background techniques related to the present invention and do not necessarily constitute prior art.

[0003] The air spring system is an advanced technology that realizes elastic buffering, shock absorption, and load-bearing functions based on the compressibility of gas. It is an important part of modern vehicle suspension technology. The improvement of its performance not only depends on advanced technology but also requires regular maintenance and monitoring to ensure its long-term stable operation.

[0004] With the development of the Internet of Things technology, currently, by integrating multi-dimensional sensors and communication modules on the vehicle, the height state, pressure state, and temperature state of the air spring system are monitored and transmitted to the cloud server for real-time status monitoring. If a preset rule (such as air pressure exceeding the threshold) is touched, an alarm is triggered.

[0005] However, relying on information such as height, pressure, and temperature to monitor the air spring system can only achieve basic state perception and cannot predict potential failures of the air spring system, which is not conducive to the pre-maintenance of the air spring system. Summary of the Invention

[0006] To solve the deficiencies of the prior art, the present invention provides a method, device, electronic device, computer-readable storage medium, and computer program product for monitoring the operation of an air spring system, continuously monitoring the operation parameters of the air spring system, and performing operation and maintenance in combination with real-time data and potential failures, improving the reliability and timeliness of operation and maintenance.

[0007] In the first aspect, the present invention provides a method for monitoring the operation of an air spring system;

[0008] A method for monitoring the operation of an air spring system includes:

[0009] Obtain the pressure information, height information, and air pump working time of the air spring system and perform time series feature extraction to determine the pressure change rate, standard deviation of the height sensor, and air pump working cycle ratio;

[0010] Process the pressure change rate, standard deviation of the height sensor, and air pump working cycle ratio through a trained isolated random forest algorithm to obtain the anomaly score of the air pump; determine the leakage flag of the air pump according to the anomaly score of the air pump and the pressure change rate;

[0011] Obtain the real-time temperature, real-time pressure, and real-time height of the air spring system, compare the real-time temperature, real-time pressure, real-time height, the abnormal score of the air pump, and the leakage flag with preset rules, and determine the fault warning level and corresponding solutions.

[0012] In some embodiments, the extraction of temporal features from the pressure information, height information, and air pump working time includes:

[0013] Based on the pressure information within a preset time window, determine the air pressure change rate according to the sampling interval and the number of data points;

[0014] Based on the height information within a preset time window, calculate the average height; according to the average height, height information, and the number of data points, determine the standard deviation of the height sensor;

[0015] According to the air pump working time and the number of data points, determine the proportion of the air pump working cycle.

[0016] In some embodiments, the specific process of processing the air pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle through the trained isolation random forest algorithm is: determine the abnormal score according to the average path length and the normalization factor traversed by the air pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle in the isolation random forest.

[0017] In some embodiments, the specific process of determining the leakage flag of the air pump according to the abnormal score of the air pump and the air pressure change rate is: if the abnormal score is greater than a preset first threshold and the air pressure change rate is less than a preset leakage determination threshold, the leakage flag is the first characteristic value; otherwise, the leakage flag is the second characteristic value.

[0018] In some embodiments, if the fault warning level is a first-level fault, the corresponding solution is after-sales maintenance; if the fault warning level is a second-level fault, the corresponding solution is remote detection and maintenance; if the fault warning level is a first-level fault, the corresponding solution is maintenance based on a preset maintenance strategy.

[0019] In some embodiments, the fault warning levels include first-level faults, second-level faults, and third-level faults, and the magnitude of the fault warning level is inversely proportional to the abnormal degree of the air spring system.

[0020] In a second aspect, the present invention provides an operating monitoring device for an air spring system;

[0021] An operating monitoring device for an air spring system, comprising:

[0022] The monitoring module is configured to: obtain the pressure information, height information, and air pump working time of the air spring system, perform time-series feature extraction, and determine the pressure change rate, height sensor standard deviation, and air pump working cycle ratio;

[0023] The air pump status prediction module is configured to: process the pressure change rate, height sensor standard deviation, and air pump working cycle ratio through a trained isolation random forest algorithm to obtain the anomaly score of the air pump; determine the leakage flag of the air pump according to the anomaly score of the air pump and the pressure change rate;

[0024] The operation warning module is configured to: obtain the real-time temperature, real-time pressure, and real-time height of the air spring system, compare the real-time temperature, real-time pressure, real-time height, the anomaly score of the air pump, and the leakage flag with preset rules, and determine the fault warning level and corresponding solutions.

[0025] In a third aspect, the present invention provides an electronic device;

[0026] An electronic device includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the above-mentioned air spring system operation monitoring method.

[0027] In a fourth aspect, the present invention provides a computer-readable storage medium;

[0028] A computer-readable storage medium has a computer program / instructions stored thereon. When the computer program / instructions are executed by a processor, the steps of the above-mentioned air spring system operation monitoring method are implemented.

[0029] In a fifth aspect, the present invention provides a computer program product;

[0030] A computer program product includes a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above-mentioned air spring system operation monitoring method are implemented.

[0031] Compared with the prior art, the beneficial effects of the present invention are:

[0032] 1. The technical solution provided by the present invention uses information such as the real-time temperature of the air spring system operation for basic perception, and combines it with the anomaly score of the air pump to comprehensively evaluate the operation state of the air spring system, improving the reliability and real-time performance of operation and maintenance.

[0033] 2. The technical solution provided by the present invention uses the Isolation Random Forest algorithm to predict the anomaly score of the air pump by using the pressure change rate, the standard deviation of the height sensor, and the duty cycle of the air pump operation. Through the joint analysis of multiple features, the monitoring strategy is detected and optimized in advance. The Isolation Random Forest algorithm can quickly isolate outliers through random segmentation, which helps to capture the few outliers reflecting the anomalies of the air pump in the above data and detect anomalies in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0035] Figure 1 It is a schematic flowchart of the air spring system operation monitoring method provided by the embodiment of the present invention;

[0036] Figure 2 It is a schematic flowchart of the air pump state prediction provided by the embodiment of the present invention;

[0037] Figure 3 It is a schematic logical diagram of the solution provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments of the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0040] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0041] Embodiment 1

[0042] The existing criteria for the operation and maintenance of air spring systems are incomplete and do not consider potential failures that may occur in the future. Therefore, this embodiment provides a method for monitoring the operation of an air spring system, which comprehensively evaluates the air spring system by combining temperature, height, air pressure, and the status of the air pump, and considers the impact of historical operating conditions on the future operating conditions of the air spring system in order to pre-warn potential failures of the air spring system.

[0043] Next, in combination with Figures 1 - 3 , a method for monitoring the operation of an air spring system disclosed in this embodiment will be described in detail. The method for monitoring the operation of the air spring system is applied to a cloud server and includes:

[0044] S1. Obtain the pressure information, height information, air pump working time, real-time temperature, real-time pressure, and real-time height of the air spring system.

[0045] In this embodiment, the pressure data is collected by a pressure sensor built into the air spring system, the temperature data is collected by a temperature sensor built into the air spring system, and the height data is collected by a height sensor built into the air spring system. The above data is transmitted to the cloud server through the mobile Internet of Things GRPS network for the data analysis described in this embodiment.

[0046] S2. Extract the time series characteristics of the pressure information, height information, and air pump working time to determine the pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle. Specifically, it includes:

[0047] S201. Based on the pressure information within a preset time window, determine the air pressure change rate according to the sampling interval and the number of data points.

[0048] Among them, the air pressure change rate ΔP is expressed as:

[0049]

[0050] In the formula, ΔP represents the air pressure change rate, N represents the number of data points within the window, and Δt represents the sampling interval.

[0051] Here, the data within the preset time window can be extracted by the sliding window method.

[0052] S202. Based on the height information within a preset time window, calculate the average height; determine the standard deviation of the height sensor according to the average height, height information, and the number of data points.

[0053] Among them, the average height is expressed as:

[0054]

[0055] The standard deviation of the height sensor is expressed as:

[0056]

[0057] In the formula, H std represents the standard deviation of the height sensor, and H t represents the value of the height sensor, and U h represents the average value collected by the height sensor.

[0058] S203. Determine the proportion of the air pump working cycle according to the working time of the air pump and the number of data points.

[0059] Among them, the proportion of the air pump working cycle is expressed as:

[0060]

[0061] In the formula, R pw represents the proportion of the air pump working cycle, and I in represents the working time of the air pump.

[0062] S204. Form a feature value sequence of the air pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle within a preset time window and perform normalization processing.

[0063] S3. Process the pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle through the trained isolated random forest algorithm to obtain the anomaly score of the air pump; determine the leakage flag of the air pump according to the anomaly score of the air pump and the pressure change rate. Specifically, it includes:

[0064] S301. Input the feature value sequence formed by the pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle into the isolated random forest algorithm for data mining, and determine the anomaly score according to the average path length and the normalization factor traversed by the pressure change rate, the standard deviation of the height sensor, and the proportion of the air pump working cycle in the isolated random forest.

[0065] In this embodiment, the trained isolated random forest algorithm is used to determine the anomaly score. The basic idea of the isolated random forest algorithm is to cut the data space by randomly selecting a feature and a random value on this feature. Each cut will generate two sub-spaces. This process will continue until there is only one data point left in each sub-space.

[0066] Before executing S301, construct a training set and a test set by collecting a large number of historical feature value sequences, train through the training set isolated random forest algorithm, and use the test set to test the training effect.

[0067] Among them, the anomaly score is expressed as:

[0068]

[0069] Wherein, E(h(x)) is the average path length of the data point x in all the trees, c(n) is the normalization factor, which is the average path length of the binary search tree composed of n points.

[0070] In this embodiment, the average of the path lengths of each isolated tree is taken to determine the average path length E(h(x)), which is expressed as:

[0071]

[0072] Wherein, h i (x) represents the path length from which the data point x traverses from the root node of the i-th isolated tree to reach the node, N represents the number of trees, and N can be N = 100.

[0073] The normalization factor c(n) is used to normalize the path length, correct the influence of the data set on the path length, and ensure that the range of the anomaly score s is between [0, 1], which is expressed as:

[0074]

[0075] Wherein, H(k) is the harmonic series, H(k) ≈ ln(k) + 0.5772, and n is the total number of samples.

[0076] Furthermore, in order to make the key features participate in harvesting more frequently and improve the accuracy and efficiency of anomaly detection, during the splitting process of the isolation random forest algorithm, weight assignment is introduced, and by assigning weights to each feature, the probability of the feature being selected is adjusted.

[0077] Define the weight variable: w = [w1 w2 w3], wherein, w1 represents the weight of the air pressure change rate, w2 represents the weight of the standard deviation of the altitude sensor, w3 represents the weight of the working cycle ratio of the air pump, and the weights satisfy the requirements. Here, the values can be taken according to experience, w = [0.5 0.3 0.2].

[0078] In order to adapt to the change of data distribution, in some embodiments, weight adjustment is performed based on dynamic feedback, and by tracking the contribution degree of the feature in the splitting process in real time, the feature selection probability is optimized, so as to improve the utilization rate of key features (such as the pressure change rate, the standard deviation of the altitude sensor). The specific process is as follows: (1) According to the feature importance, set the initial value of the weight variable based on the empirical value. For example, w = [0.5 0.3 0.2].

[0079] (2) When splitting the nodes of each tree, randomly select candidate features based on the initial weights. If the feature is selected and the path length is shortened after splitting, calculate the path shortening amount, update its contribution degree and convert it into the feature selection probability.

[0080] Among them, the path shortening amount ΔL i is expressed as:

[0081] ΔL i = L parent - L child ;

[0082] The contribution update formula is expressed as:

[0083]

[0084] The feature selection probability P i is expressed as:

[0085]

[0086] In the formula, L parent represents the path length of the parent node, L child represents the path length of the child node, represents the cumulative contribution degree of the i-th feature after the t-th iteration, α represents the attenuation factor (1 ≥ α ≥ 0), which controls the retention ratio of historical contributions, L BASE represents the benchmark path length of the current data set (usually taking the logarithm of the number of training samples), β represents the temperature coefficient (β > 0), which controls the steepness of the probability distribution. The larger β is, the more significant the selection probability of high-contribution features is, and d represents the total number of features.

[0087] S302. Determine the leakage flag of the air pump according to the abnormal score and pressure change rate of the air pump.

[0088] In this embodiment, the leakage flag LF is defined as a binary variable (0 or 1), which is used to directly determine whether there is gas leakage when the air pump is working. When it is equal to 1, there is leakage; the leakage flag LF is expressed as:

[0089]

[0090] In the formula, LF is the leakage flag, and r is the leakage determination threshold, which takes a value of 0.3 KPa / s here.

[0091] As an implementation manner, before executing S3, it further includes:

[0092] Collect the data of the pressure, height change and air pump working time under the normal operation of the air spring as the original data, use the sliding window method to extract the time series features of the data respectively, and add the abnormal score label to form a training set. Input the training set into the isolation random forest algorithm for data mining. Each data in the data has to pass through each tree to obtain the path length and average path length under each tree until the training is completed.

[0093] S4. Compare the real-time temperature, real-time pressure, real-time altitude, the anomaly score of the air pump, and the leakage flag with the preset rules to determine the fault warning level and the corresponding solution.

[0094] In this embodiment, the fault warning levels include primary faults, secondary faults, and tertiary faults. The magnitude of the fault warning level is inversely proportional to the degree of anomaly of the air spring system. The main primary fault situations are: (1) When an open circuit or short circuit is detected in the altitude, temperature, or pressure sensor; (2) When the value collected by the altitude sensor exceeds the set threshold; (3) The air pump fails to work. The main secondary faults are: abnormal adjustment or non-adjustment of the air spring during driving or normal use. At this time, the system reads the fault information and sends the information to the vehicle owner and the monitoring and maintenance personnel. After the monitoring and maintenance personnel contact the vehicle owner, remote detection and maintenance are carried out. The main tertiary faults are: the operating temperature of the air pump exceeds the threshold, or the opening time of the air spring valve is too long. At this time, the air spring adjustment is temporarily stopped.

[0095] Exemplarily, when it is detected that the air pump is not started, i.e., R pw = 0, the air pressure continuously drops, it is determined that the air spring leaks, and at this time, a primary fault is reported; when it is detected that the air pump works for a long time, i.e., R pw > 0.8, and the fluctuation is large, at this time, the air pump works frequently and the air pressure is abnormal, and at this time, a primary fault is reported; when the value of s is in the range of (0.5 < s ≤ 0.6) and LF = 0, at this time, the working time of the air pump is slightly extended and the data of the altitude sensor is slightly abnormal, and a tertiary fault is reported, only for attention; when the value of s is in the range of (0.6 < s ≤ 0.8) and LF = 0, the working time of the air pump is significantly extended and the data of the altitude sensor fluctuates greatly, and a secondary fault is reported; when the value of s is in the range of (s ≥ 0.8), at this time, the air pump fails, and a primary fault is reported and inspection is required.

[0096] By obtaining the signal values of the vehicle altitude, temperature, and pressure sensors in real time and judging the corresponding states, if the received signal value is within the preset interval, it is considered valid, otherwise it is considered invalid; if the received signal is invalid, it is considered that the vehicle sensor signal is in a lost state, and at this time, a primary fault is reported; if the received signal is valid, the judgment of the next stage state is entered.

[0097] Furthermore, when a primary fault occurs, temporary treatment is carried out for the primary situation that appears, and the pressure in the air spring is monitored in real time, the adjustment of the air spring is restricted, and the vehicle owner is remotely notified to go to the 4S shop for repair and inspection.

[0098] When an open or short circuit is detected in the height, temperature, or pressure sensor, the adjustment of the air spring system is restricted, and the pressure of the air spring system is adjusted. If the pressure threshold of a certain air spring is lower than the set minimum threshold, the pressure of other wheels is adjusted to the minimum threshold; if the pressure threshold of the air spring is higher than the set minimum threshold, the adjustment is based on the pressure value of the lowest air spring. When the value collected by the height sensor exceeds the set threshold, adjust it with reference to other height sensors until it reaches the standard position. If all height sensors are damaged, stop the adjustment and maintain this state. When the air pump cannot work, the air spring temporarily stops adjusting.

[0099] When a secondary fault occurs, remote detection and maintenance by the staff are required.

[0100] When a tertiary fault occurs, air spring maintenance is carried out based on a preset maintenance strategy. Specifically, the value collected by the temperature sensor is monitored in real time. When the collected temperature is greater than the set threshold Team1, the air pump stops working and only resumes working until the temperature drops to the set temperature threshold Team2.

[0101] When the collected temperature is less than (set threshold Team1 - 5°C) and the working time of the air spring valve exceeds 3 minutes, the air pump stops working and only resumes working until the temperature drops to the set temperature threshold Team2 or the stationary time exceeds 6 minutes. When the collected temperature is less than (set threshold Team1 - 10°C) and the working time of the air spring valve exceeds 5 minutes, the air pump stops working and only resumes working until the temperature drops to the set temperature threshold Team2 or the stationary time exceeds 8 minutes. When the collected temperature is less than (set threshold Team1 - 15°C) and the working time of the air spring valve exceeds 6 minutes, the air pump stops working and only resumes working until the temperature drops to the set temperature threshold Team2 or the stationary time exceeds 10 minutes.

[0102] Furthermore, the cloud server will collect and store the maintenance history records of all vehicles, including the data of each detection, repair records, and detailed information of replaced parts. These data will provide a historical reference for vehicle maintenance, helping technicians better understand the operating conditions of the vehicles and formulate personalized maintenance plans.

[0103] Embodiment 2

[0104] This embodiment discloses an operating monitoring device for an air spring system, including:

[0105] A monitoring module, configured to: obtain the pressure information, height information, and air pump working time of the air spring system, extract time series features, and determine the pressure change rate, standard deviation of the height sensor, and air pump working cycle ratio;

[0106] An air pump status prediction module, configured to: process the pressure change rate, the standard deviation of the altitude sensor, and the air pump working cycle ratio through a trained isolated random forest algorithm to obtain the anomaly score of the air pump; determine the leakage flag of the air pump according to the anomaly score of the air pump and the pressure change rate;

[0107] An operation warning module, configured to: obtain the real-time temperature, real-time pressure, and real-time altitude of the air spring system, compare the real-time temperature, real-time pressure, real-time altitude, the anomaly score of the air pump, and the leakage flag with preset rules to determine the fault warning level and the corresponding solution.

[0108] It should be noted here that the above monitoring module, air pump status prediction module, and operation warning module correspond to the steps in Embodiment 1. The examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0109] Embodiment 3

[0110] Embodiment 3 of the present invention provides an electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the above air spring system operation monitoring method are completed.

[0111] Embodiment 4

[0112] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above air spring system operation monitoring method are completed.

[0113] Embodiment 5

[0114] Embodiment 5 of the present invention provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above air spring system operation monitoring method are implemented.

[0115] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the processFigure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0116] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device to perform a series of operation steps on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0118] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for monitoring the operation of an air spring system, characterized in that: include: Obtain the pressure information, height information and air pump working time of the air spring system and extract the time series features to determine the pressure change rate, height sensor standard deviation and air pump working cycle ratio; The pressure change rate, the standard deviation of the altitude sensor, and the proportion of the air pump working cycle are processed by the trained isolated random forest algorithm to obtain the abnormal score of the air pump; based on the abnormal score and the pressure change rate of the air pump, the leakage sign of the air pump is determined; Obtain the real-time temperature, real-time pressure and real-time height of the air spring system, compare the real-time temperature, real-time pressure and real-time height as well as the abnormal score and leakage mark of the air pump with the preset rules, and determine the fault warning level and corresponding solution.

2. The air spring system operation monitoring method according to claim 1, characterized in that: The temporal feature extraction of pressure information, altitude information and air pump working time includes: Based on the pressure information within a preset time window, the pressure change rate is determined according to the sampling interval and the number of data points; Calculate the average height based on the height information within the preset time window; determine the standard deviation of the height sensor based on the average height, the height information and the number of data points; Determine the air pump duty cycle ratio based on the air pump working time and the number of data points.

3. The air spring system operation monitoring method according to claim 1, characterized in that: The processing of the pressure change rate, the standard deviation of the altitude sensor and the proportion of the air pump working cycle by the trained isolated random forest algorithm is specifically as follows: determining the abnormal score according to the average path length and the normalization factor traversed by the pressure change rate, the standard deviation of the altitude sensor and the proportion of the air pump working cycle in the isolated random forest.

4. The air spring system operation monitoring method according to claim 1, characterized in that: The method of determining the leakage mark of the air pump based on the abnormality score and pressure change rate of the air pump is specifically as follows: if the abnormality score is greater than a preset first threshold and the pressure change rate is less than a preset leakage judgment threshold, the leakage mark is a first characteristic value; otherwise, the leakage mark is a second characteristic value.

5. The air spring system operation monitoring method according to claim 1, characterized in that: If the fault warning level is level one, the corresponding solution is after-sales maintenance; If the fault warning level is level 2, the corresponding solution is remote detection and maintenance; If the fault warning level is a level one fault, the corresponding solution is to perform maintenance based on a preset maintenance strategy.

6. The air spring system operation monitoring method according to claim 1, characterized in that: The fault warning levels include primary fault, secondary fault and tertiary fault, and the magnitude of the fault warning level is inversely proportional to the degree of abnormality of the air spring system.

7. An air spring system operation monitoring device, characterized in that: include: The monitoring module is configured to: obtain pressure information, height information and air pump working time of the air spring system and perform time series feature extraction to determine the pressure change rate, height sensor standard deviation and air pump working cycle ratio; The air pump state prediction module is configured to: process the pressure change rate, the standard deviation of the altitude sensor and the air pump duty cycle ratio through the trained isolated random forest algorithm to obtain the abnormal score of the air pump; determine the leakage sign of the air pump according to the abnormal score and the pressure change rate of the air pump; The operation warning module is configured to obtain the real-time temperature, real-time pressure and real-time height of the air spring system, compare the real-time temperature, real-time pressure and real-time height as well as the abnormal score and leakage mark of the air pump with the preset rules, and determine the fault warning level and corresponding solution.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the air spring system operation monitoring method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the air spring system operation monitoring method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the air spring system operation monitoring method according to any one of claims 1 to 6 are implemented.

Images