Data processing method and system for integrated electronic control device

Abstract

The present invention relates to the field of data processing technology, and in particular to a data processing method and system for an integrated electric control device. The method comprises the steps of: obtaining the initial interval number of a histogram according to the number and discreteness of current data to obtain a histogram; obtaining the distribution uniformity of each interval of the histogram according to the abnormal possibility of each data in each interval of the histogram; obtaining the necessity of splitting each interval of the histogram according to the distribution uniformity, splitting each interval to obtain an updated histogram; obtaining the merging property of each interval of the updated histogram according to the similarity between the intervals of the updated histogram and the data difference between the interval and its similar interval, merging the intervals to obtain a final histogram; obtaining the abnormal score of each current data according to the final histogram, and performing abnormal detection. The present invention makes the HBOS algorithm more accurate in monitoring abnormal data and improves the results of abnormal detection.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data processing method and system for an integrated electric control device. Background Art

[0002] An integrated electronic control device refers to an organic combination of electronic components and mechanical equipment to form an intelligent control device with electronic system control as the core. It has efficient, accurate and reliable control functions and has been applied in many fields. Industrial automation is an important application field of integrated electronic control devices. It can realize intelligence, efficiency and integration in industrial production, improve production efficiency and quality. For example, automated production lines, automated sorting systems and robot control systems are inseparable from the support of integrated electronic control devices. In the process of industrial automation production, when key equipment such as motors shut down or malfunction, the entire production line will be affected. Therefore, by collecting current data during the operation of the motor for real-time monitoring and abnormality monitoring, problems can be discovered in the early stages of the fault, which is convenient for staff to deal with the fault in time and improve the overall operation efficiency of the production line.

[0003] The patent application document with the publication number CN116608904A currently discloses a real-time monitoring method and system for the safety status of a hydrogen storage tank, which collects the temperature data sequence and strain data sequence of the monitoring point in the hydrogen storage tank within the initial monitoring period; determines the compression time when the hydrogen in the hydrogen storage tank starts to be compressed based on the strain data sequence of the monitoring point in the initial monitoring period; calculates the first interval division number based on the temperature abnormality degree corresponding to the temperature data sequence after the compression moment; calculates the second interval division number based on the strain abnormality degree corresponding to the strain data sequence after the compression moment; uses the HBOS abnormality monitoring algorithm to perform abnormality monitoring on the temperature data sequence based on the first interval division number, and uses the HBOS abnormality monitoring algorithm to perform abnormality monitoring on the temperature data sequence based on the second interval division number.

[0004] When the HBOS algorithm detects anomalies in current data, it is necessary to first divide the value range of the current data into intervals to construct a histogram, estimate the probability density of each current data based on the histogram, and use this as a basis to obtain the anomaly score of each current data to complete the detection of abnormal data. However, since the number of abnormal data contained in the collected current data is unclear, if the number of preset histogram intervals is too many or too few, the estimation of the data probability density will be inaccurate, affecting the detection of abnormal data. In addition, the current data generated by the increase or decrease of the load is similar to the larger or smaller current data generated by the abnormal motor equipment, and it is very likely that they will be divided into the same interval of the histogram, resulting in the identification of normal data and abnormal data as the same type of data. Summary of the invention

[0005] In order to solve the technical problem that the current data generated by the increase or decrease of the load of the motor equipment is similar to the current data generated by the abnormality of the motor equipment, and the HBOS algorithm is used for abnormality detection, it is very likely to divide them into the same interval of the histogram, affecting the abnormality detection, the present invention provides a data processing method and system for an integrated electric control device.

[0006] In a first aspect, the present invention provides a data processing method for an integrated electronic control device, which adopts the following technical solution:

[0007] A data processing method for an integrated electronic control device comprises the following steps:

[0008] Collect current data, obtain the initial number of intervals of the histogram, and construct the histogram; obtain the necessity of splitting each interval of the histogram:

[0009] ; Represents the necessity of splitting the i-th interval of the histogram; Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the maximum value of the contrast degree of the i-th interval of the histogram under all division thresholds; Represents the number of division thresholds for the i-th interval of the histogram; as well as represents the contrast degree of the ith interval of the histogram under the vth partition threshold and the v+1th partition threshold; exp() represents an exponential function with a natural constant as the base; norm() represents a normalization function; the interval is split based on the necessity of the split to obtain an updated histogram; the mergeability of each interval of the updated histogram is obtained:

[0010] , Represents the mergeability of the ath interval of the updated histogram; as well as Represents the degree of abnormality of the ath interval and the a+1th interval of the updated histogram; as well as Representing the average of the number of data in the ath interval of the updated histogram and the number of data in the similar intervals of the ath interval; merging the intervals based on the merging property to obtain a final histogram; and identifying abnormal data according to the final histogram.

[0011] The innovation of the present invention lies in that, first, according to the discrete degree of current data distribution, the initial interval number of the histogram is adaptively obtained, and a histogram is constructed, taking into account the discrete degree of current data distribution, so that the initial interval number of the histogram obtained can fit the current data distribution, thereby improving the detection result of abnormal data; next, according to the difference between the current data generated by load increase or decrease and the larger or smaller current data generated by the abnormal motor equipment, the abnormal possibility of each data in each interval of the histogram is obtained, and the single distribution of each interval of the histogram is further obtained, and then the necessity of splitting each interval of the histogram is obtained based on the single distribution to split the interval, so that the current data generated by load increase or decrease can be distinguished from the larger or smaller current data generated by the abnormal motor equipment, thereby improving the correctness of abnormal data detection; finally, in order to avoid detecting a small interval composed of current data generated in the load conversion process as abnormal data, the histograms with a smaller number of data are merged to obtain a final histogram for abnormal data identification, thereby improving the accuracy of abnormal data detection.

[0012] Preferably, the obtaining of the initial interval number of the histogram and constructing the histogram comprises:

[0013] ;

[0014] In the formula, D represents the initial interval number of the histogram; Represents the number of current data; Represents the discreteness of current data distribution; Represents the floor symbol.

[0015] Using the HBOS algorithm, the value range of the current data is used as the horizontal axis and the number of data is used as the vertical axis to construct a histogram. The value range of the current data is divided into various intervals according to the initial interval number of the histogram, and then each current data is assigned to the interval corresponding to the histogram.

[0016] The discrete degree of current data distribution is taken into consideration so that the initial interval number of the acquired histogram can fit the current data distribution and improve the detection result of abnormal data.

[0017] Preferably, obtaining the distribution uniformity of the interval includes:

[0018] Get the abnormal probability of each data in each interval of the histogram;

[0019] ;

[0020] In the formula, Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the number of data in the i-th interval of the histogram; Represents the mean of the abnormal probability of all data in the i-th interval of the histogram; Represents the range of abnormal probability of all data in the i-th interval of the histogram; || represents the absolute value symbol; exp() represents an exponential function with a natural constant as the base.

[0021] It can reflect the types of data in each interval. The larger the value, the more likely it is to contain normal data and abnormal data, which is convenient for subsequent splitting.

[0022] Preferably, the step of obtaining the abnormal possibility of each data in each interval of the histogram includes:

[0023] ;

[0024] In the formula, Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the value of the jth data in the i-th interval of the histogram; Represents the mean of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the maximum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the minimum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the number of extreme points in the neighborhood data of the jth data in the i-th interval of the histogram; Represents the Pearson correlation coefficient between the neighborhood data of the jth data in the i-th interval of the histogram and the torque data at the corresponding sampling time.

[0025] This facilitates the subsequent acquisition of the distribution uniformity of each interval of the histogram.

[0026] Preferably, obtaining the contrast degree of the interval under all division thresholds includes:

[0027] Arrange the abnormal possibility of each data in the i-th interval of the histogram from small to large to obtain the abnormal sequence of the i-th interval of the histogram, take each data in the abnormal sequence of the i-th interval of the histogram as a division threshold, and obtain the division threshold of the i-th interval of the histogram. For any division threshold, use the division threshold to divide the abnormal sequence of the i-th interval of the histogram into two interval segments, and record the absolute value of the difference between the means of all data in the two interval segments as the contrast degree of the i-th interval of the histogram under the division threshold.

[0028] Preferably, the step of splitting the interval based on the necessity of the split to obtain an updated histogram includes:

[0029] A split necessity threshold T2 is preset. If the split necessity of the ith interval of the histogram is greater than the split necessity threshold T2, the value of the current data corresponding to the split threshold corresponding to the maximum value of the contrast degree of the ith interval of the histogram under all split thresholds is obtained, and recorded as the split value of the ith interval. The ith interval is divided into two intervals according to the split value to obtain an updated histogram.

[0030] It can distinguish the current data generated by load increase or decrease from the larger or smaller current data generated by abnormal motor equipment, thereby improving the accuracy of abnormal data detection.

[0031] Preferably, obtaining the similar interval of the interval includes:

[0032] Obtain the mean value of the abnormal probability of all data in each interval of the updated histogram, and record it as the abnormal degree of each interval of the updated histogram;

[0033] A difference threshold is preset, and the absolute value of the difference between the abnormality degree of the ath interval of the updated histogram and each other interval of the updated histogram is obtained, and the interval whose absolute value of the difference is less than the difference threshold is recorded as a similar interval of the ath interval of the updated histogram.

[0034] Preferably, the merging of intervals based on the merging property to obtain a final histogram includes:

[0035] A merging necessity threshold T4 is preset. If the merging of any interval of the updated histogram is greater than the merging necessity threshold T4, the interval of the updated histogram is merged with the next interval of the interval to obtain a final histogram.

[0036] Avoid detecting a small section of current data generated during the load conversion process as abnormal data.

[0037] Preferably, the identifying of abnormal data according to the final histogram includes:

[0038] The HBOS algorithm is used to obtain the probability density of each current data according to the final histogram, and the inverse of the probability density of each current data is used as the abnormality score of each current data. The abnormality score threshold T5 is preset. If the abnormality score of any current data is greater than the abnormality score threshold T5, the current data is abnormal data.

[0039] In a second aspect, the present invention provides a data processing system for an integrated electronic control device, which adopts the following technical solution:

[0040] A data processing system for an integrated electronic control device comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned data processing method for an integrated electronic control device is implemented.

[0041] By adopting the above technical solution, the above-mentioned integrated electronic control device generates a computer program using a data processing method and stores it in a memory to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0042] The present invention has the following technical effects: the purpose of the present invention is to first adaptively obtain the initial interval number of the histogram according to the discrete degree of current data distribution, construct a histogram, take into account the discrete degree of current data distribution, so that the initial interval number of the histogram obtained can fit the current data distribution, improve the detection result of abnormal data, then obtain the abnormal possibility of each data in each interval of the histogram according to the difference between the current data generated by the load increase or decrease and the larger or smaller current data generated by the abnormal motor equipment, further obtain the single distribution of each interval of the histogram, and then obtain the necessity of splitting each interval of the histogram based on the single distribution to split the interval, so that the current data generated by the load increase or decrease can be distinguished from the larger or smaller current data generated by the abnormal motor equipment, thereby improving the correctness of abnormal data detection; finally, in order to avoid detecting the small interval composed of the current data generated in the load conversion process as abnormal data, the histograms with a smaller number of data are merged to obtain the final histogram for abnormal data identification, thereby improving the accuracy of abnormal data detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0044] Figure 1 It is a method flow chart of a data processing method for an integrated electric control device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0047] The embodiment of the present invention discloses a data processing method for an integrated electric control device, referring to Figure 1 , comprising steps S1 to S3:

[0048] S1: Collect current data.

[0049] In the embodiment of the present invention, the sampling time is preset to 2 seconds / time, a current sensor and a torque sensor are installed on the motor equipment, current data and torque data are collected, the current data at each sampling time constitutes a current data sequence, the torque data at each sampling time constitutes a torque data sequence, and the current data in the current data sequence is standardized;

[0050] S2: According to the number of current data and the degree of discreteness of the current data, the initial number of intervals of the histogram is adaptively obtained, and then the current data is distributed to the intervals corresponding to the histogram to obtain a histogram; the abnormal possibility of each data in each interval of the histogram is obtained, and according to the abnormal possibility, the distribution uniformity of each interval of the histogram is obtained.

[0051] Step S2 includes steps S20 and S21, which are specifically as follows:

[0052] S20: adaptively acquiring the initial number of intervals of the histogram according to the number of current data and the degree of discreteness of the current data, and then allocating the current data to intervals corresponding to the histogram to obtain a histogram.

[0053] It should be noted that when the HBOS algorithm performs anomaly detection on current data, it is necessary to first divide the value range of the current data into various intervals to construct a histogram, estimate the probability density of each current data based on the histogram, and use this as a basis to obtain the anomaly score of each current data to complete the detection of abnormal data. However, since the collected current data contains abnormal data, it is inaccurate to directly manually set the number of intervals of the histogram. If the number of intervals is too large, the details of the current data distribution may be lost; if the number of intervals is too small, there may be too few data points in each interval, resulting in inaccurate estimation of the data probability density. Therefore, the present invention first adaptively obtains the initial number of intervals of the histogram according to the number of current data, and then analyzes the degree of discreteness of the current data. If the degree of discreteness of the current data is greater, it means that the current data as a whole is more volatile. It is necessary to increase the initial number of intervals of the histogram according to the degree of discreteness of the current data distribution to adapt to data fluctuations.

[0054] In this embodiment of the present invention, the initial interval number of the histogram is obtained:

[0055] ;

[0056] In the formula, D represents the initial interval number of the histogram; represents the number of current data; it is known that the number of intervals of current data is positively correlated with the number of current data, so firstly, the initial number of intervals of the histogram is obtained according to the number of current data; Represents the discreteness of current data distribution; Represents the downward value symbol; the more discrete the distribution of current data is, the more volatile the current data is as a whole. At this time, the number of initial intervals of the histogram needs to be increased according to the degree of discreteness of the current data distribution; if the distribution of current data is relatively concentrated, it means that the current data is more aggregated as a whole. At this time, the number of initial intervals of the histogram needs to be increased according to the degree of discreteness of the current data distribution.

[0057] Using the HBOS algorithm, the value range of the current data is used as the horizontal axis and the number of data is used as the vertical axis to construct a histogram. The value range of the current data is divided into various intervals according to the initial interval number of the histogram, and then each current data is assigned to the interval corresponding to the histogram to obtain a histogram.

[0058] S21: Obtain the abnormal possibility of each data in each interval of the histogram, and obtain the distribution uniformity of each interval of the histogram based on the abnormal possibility.

[0059] It should be noted that when the motor equipment is operating normally, the current data collected should be relatively stable. However, if the load of the motor is unstable or there is a problem with the motor control system, the current data will fluctuate irregularly and the current at this time will be significantly higher or lower than the current value during normal operation. The known load refers to the equipment or device connected to the motor shaft, driven by the motor and consuming the motor power. For example, in industrial scenarios, motor-driven conveyor belts, water pumps, fans, etc. are all motor loads, and the motor current is closely related to the load. When the load driven by the motor increases, the motor needs to output a larger torque to maintain the operation of the load. According to the relationship between the motor torque and current (positive correlation), when the motor load increases and is not overloaded, the current data will gradually increase and then stabilize. When the motor load gradually decreases, the current data will gradually decrease and then stabilize.

[0060] Therefore, since the current data generated by load increase or decrease is similar to the larger or smaller current data generated by the abnormal motor equipment, they are likely to be divided into the same interval of the histogram. The HBOS algorithm estimates the probability density of each current data based on the histogram and then performs anomaly detection. Therefore, it is very likely to identify normal data and abnormal data as the same type of data. Therefore, the present invention first analyzes the data in each interval of the histogram to obtain the distribution uniformity of each interval of the histogram, so as to facilitate the subsequent splitting of the intervals containing two types of data in the histogram according to the distribution uniformity.

[0061] In the embodiment of the present invention, the first N data and the last N data of each data in each interval of the histogram in the current data sequence are used as the neighborhood data of each data in each interval of the histogram.

[0062] Get the anomaly probability of each data in each interval of the histogram:

[0063] ;

[0064] In the formula, Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the value of the jth data in the i-th interval of the histogram; Represents the mean of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the maximum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the minimum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the number of extreme points in the neighborhood data of the jth data in the i-th interval of the histogram; The Pearson correlation coefficient between the neighborhood data of the jth data in the i-th interval of the histogram and the torque data at the corresponding sampling time;

[0065] Get the uniformity of the distribution for each bin of a histogram:

[0066] ;

[0067] In the formula, Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the number of data in the i-th interval of the histogram; Represents the mean of the abnormal probability of all data in the i-th interval of the histogram; Represents the extreme value of the abnormal probability of all data in the i-th interval of the histogram; || represents the absolute value symbol; exp() represents an exponential function with a natural constant as the base; The larger the value of , the more likely there are two types of data (normal data and abnormal data) in the i-th interval of the histogram. At this time, the distribution uniformity of the i-th interval of the histogram is smaller. The larger the value of , the more likely there are two types of data (normal data and abnormal data) in the i-th interval of the histogram. At this time, the distribution uniformity of the i-th interval of the histogram is smaller.

[0068] S3: According to the distribution uniformity of each interval of the histogram and the degree of contrast after each interval is split, the necessity of splitting each interval of the histogram is obtained, and each interval is split to obtain an updated histogram; according to the similarity between each interval of the updated histogram and its next interval and the data difference between each interval and its similar interval, the merging property of each interval of the updated histogram is obtained, and they are merged to obtain a final histogram; according to the final histogram, the abnormal score of each current data is obtained, and then the abnormal data is obtained.

[0069] Step S3 includes steps S30 and S31, which are specifically as follows:

[0070] S30: According to the distribution uniformity of each interval of the histogram and the degree of contrast after each interval is split, the necessity of splitting each interval of the histogram is obtained, and each interval is split to obtain an updated histogram; according to the similarity between each interval of the updated histogram and its next interval and the data difference between each interval and its similar interval, the merging property of each interval of the updated histogram is obtained, and they are merged to obtain a final histogram.

[0071] It should be noted that the distribution uniformity of each interval of the histogram is obtained. The smaller the value, the more the interval should be split. Then, each interval is divided into two interval segments according to the abnormal possibility of the data in each interval. The difference in the mean of the abnormal possibility of the data in the two interval segments is used to determine whether the interval should be split.

[0072] In an embodiment of the present invention, the abnormal possibility of each data in the i-th interval of the histogram is arranged from small to large to obtain the abnormal sequence of the i-th interval of the histogram, and each data of the abnormal sequence of the i-th interval of the histogram is used as a division threshold to obtain the division threshold of the i-th interval of the histogram. For any division threshold, the abnormal sequence of the i-th interval of the histogram is divided into two interval segments using the division threshold, and the absolute value of the difference between the means of all data in the two interval segments is recorded as the contrast degree of the i-th interval of the histogram under the division threshold.

[0073] Get the necessity of splitting each bin of the histogram:

[0074] ;

[0075] In the formula, Represents the necessity of splitting the i-th interval of the histogram; Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the maximum value of the contrast degree of the i-th interval of the histogram under all division thresholds; Represents the number of division thresholds for the i-th interval of the histogram; Represents the contrast degree of the i-th interval of the histogram under the v-th division threshold; Represents the contrast degree of the i-th interval of the histogram under the v+1-th division threshold; the greater the splitting of the i-th interval of the histogram, the more likely it is that the interval contains both normal data and abnormal data, and therefore the interval should be split.

[0076] A split necessity threshold T2 is preset. If the split necessity of the ith interval of the histogram is greater than the split necessity threshold T2, the value of the current data corresponding to the split threshold corresponding to the maximum value of the contrast degree of the ith interval of the histogram under all split thresholds is obtained, and recorded as the split value of the ith interval. The ith interval is divided into two intervals according to the split value. At this point, an updated histogram is obtained. In an embodiment of the present invention, the split necessity threshold T2 is preset to 0.7. In other embodiments, the implementer may preset the value of the split necessity threshold according to the specific implementation method.

[0077] It should be noted that it is known that the load of the motor may change during operation, so the collected current data may be of multiple types. Therefore, the current data generated during the load conversion process will constitute some small intervals, and the amount of data in each interval is small, which affects the data anomaly detection. Therefore, it is necessary to merge this type of boxes to more clearly compare the current distribution under different load conditions. After the above operation splits the box, it may also generate some small normal data intervals, which also need to be merged in order to make the anomaly detection accurate.

[0078] In an embodiment of the present invention, the mean of the abnormal probability of all data in each interval of the updated histogram is obtained, recorded as the abnormal degree of each interval of the updated histogram, the absolute value of the difference between the abnormal degree of the ath interval of the updated histogram and each other interval is obtained, and the interval with the absolute value of the difference less than T3 is recorded as the similar interval of the ath interval of the updated histogram. The preset difference threshold T3=0.2, in other embodiments, the implementer can preset the value of the difference threshold according to the specific implementation method.

[0079] Get the mergeability of each bin of the updated histogram:

[0080] ;

[0081] In the formula, Represents the mergeability of the ath interval of the updated histogram; Represents the abnormality level of the ath interval of the updated histogram; Represents the abnormality level of the a+1th interval of the updated histogram; represents the similarity between the ath interval and the a+1th interval of the updated histogram; || represents the absolute value symbol; Represents the number of data in the ath interval of the updated histogram; Represents the mean of the number of data in all similar intervals of the a-th interval of the updated histogram; if the number of data in the a-th interval of the updated histogram is smaller and the difference with the mean of the number of data in its similar intervals is greater, it means that the area should be merged more; if the a-th interval of the updated histogram is more similar to its a+1-th interval, it means that they should be merged more. The larger the value is, the more the a-th interval of the updated histogram should be merged.

[0082] A merge necessity threshold T4 is preset. If the mergeability of any interval of the update histogram is greater than the merge necessity threshold T4, the interval of the update histogram is merged with the next interval of the interval to obtain a final histogram. The merge necessity threshold T4 is preset to 0.7. In other embodiments, the implementer may preset the value of the difference threshold according to the specific implementation method.

[0083] S31: According to the final histogram, an abnormal score of each current data is obtained, and then abnormal data is obtained.

[0084] In an embodiment of the present invention, the HBOS algorithm is used to obtain the probability density of each current data according to the final histogram, and the inverse of the probability density of each current data is used as the abnormality score of each current data. The abnormality score threshold T5 is preset. If the abnormality score of any current data is greater than the abnormality score threshold T5, the current data is abnormal data. At this time, the motor equipment may fail, and the staff is notified for maintenance.

[0085] The abnormal score threshold T5 is preset to be 0.64. In other embodiments, implementers may preset the abnormal score threshold according to specific implementation methods.

[0086] An embodiment of the present invention further discloses a data processing system for an integrated electronic control device, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a data processing method for an integrated electronic control device according to the present invention is implemented.

[0087] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0088] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0089] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0090] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method for an integrated electronic control device, characterized in that: Includes steps: Collect current data, obtain the initial number of intervals of the histogram, and construct the histogram; obtain the necessity of splitting each interval of the histogram: ; Represents the necessity of splitting the i-th interval of the histogram; Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the maximum value of the contrast degree of the i-th interval of the histogram under all division thresholds; Represents the number of division thresholds for the i-th interval of the histogram; as well as represents the contrast degree of the ith interval of the histogram under the vth partition threshold and the v+1th partition threshold; exp() represents an exponential function with a natural constant as the base; norm() represents a normalization function; the interval is split based on the necessity of the split to obtain an updated histogram; the mergeability of each interval of the updated histogram is obtained: , Represents the mergeability of the ath interval of the updated histogram; as well as Represents the degree of abnormality of the ath interval and the a+1th interval of the updated histogram; as well as Represents the average of the number of data in the ath interval of the updated histogram and the number of data in the similar intervals of the ath interval; and merges the intervals based on the mergeability to obtain a final histogram; Based on the final histogram, identify abnormal data.

2. A data processing method for an integrated electronic control device according to claim 1, characterized in that: The step of obtaining the initial interval number of the histogram and constructing the histogram includes: ； Where D represents the initial interval number of the histogram; Represents the number of current data; Represents the discreteness of the current data distribution; Represents the floor symbol; Using the HBOS algorithm, the value range of the current data is used as the horizontal axis and the number of data is used as the vertical axis to construct a histogram. The value range of the current data is divided into various intervals according to the initial interval number of the histogram, and then each current data is assigned to the interval corresponding to the histogram.

3. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The acquisition of the distribution uniformity of the interval includes: Get the abnormal probability of each data in each interval of the histogram; ； In the formula, Represents the uniformity of the distribution of the i-th interval of the histogram; Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the number of data in the i-th interval of the histogram; Represents the mean of the abnormal probability of all data in the i-th interval of the histogram; Represents the range of abnormal probability of all data in the i-th interval of the histogram; || represents the absolute value symbol; exp() represents an exponential function with a natural constant as the base.

4. The data processing method for an integrated electronic control device according to claim 3, characterized in that: The obtaining of the abnormal possibility of each data in each interval of the histogram includes: ； In the formula, Represents the abnormal possibility of the jth data in the i-th interval of the histogram; Represents the value of the jth data in the i-th interval of the histogram; Represents the mean of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the maximum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the minimum value of the neighborhood data of the jth data in the i-th interval of the histogram; Represents the number of extreme points in the neighborhood data of the jth data in the i-th interval of the histogram; Represents the Pearson correlation coefficient between the neighborhood data of the jth data in the i-th interval of the histogram and the torque data at the corresponding sampling time.

5. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The acquisition of the contrast degree of the interval under all division thresholds includes: Arrange the abnormal possibility of each data in the i-th interval of the histogram from small to large to obtain the abnormal sequence of the i-th interval of the histogram, take each data in the abnormal sequence of the i-th interval of the histogram as a division threshold, and obtain the division threshold of the i-th interval of the histogram. For any division threshold, use the division threshold to divide the abnormal sequence of the i-th interval of the histogram into two interval segments, and record the absolute value of the difference between the means of all data in the two interval segments as the contrast degree of the i-th interval of the histogram under the division threshold.

6. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The step of splitting the interval based on the necessity of the split to obtain an updated histogram includes: A split necessity threshold T2 is preset. If the split necessity of the ith interval of the histogram is greater than the split necessity threshold T2, the value of the current data corresponding to the split threshold corresponding to the maximum value of the contrast degree of the ith interval of the histogram under all split thresholds is obtained, and recorded as the split value of the ith interval. The ith interval is divided into two intervals according to the split value to obtain an updated histogram.

7. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The acquisition of a similar interval to the interval includes: Obtain the mean value of the abnormal probability of all data in each interval of the updated histogram, and record it as the abnormal degree of each interval of the updated histogram; A difference threshold is preset, and the absolute value of the difference between the abnormality degree of the ath interval of the updated histogram and each other interval of the updated histogram is obtained, and the interval whose absolute value of the difference is less than the difference threshold is recorded as a similar interval of the ath interval of the updated histogram.

8. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The step of merging the intervals based on the merging property to obtain a final histogram includes: A merging necessity threshold T4 is preset. If the merging of any interval of the updated histogram is greater than the merging necessity threshold T4, the interval of the updated histogram is merged with the next interval of the interval to obtain a final histogram.

9. The data processing method for an integrated electronic control device according to claim 1, characterized in that: The method of identifying abnormal data according to the final histogram includes: The HBOS algorithm is used to obtain the probability density of each current data according to the final histogram, and the inverse of the probability density of each current data is used as the abnormality score of each current data. The abnormality score threshold T5 is preset. If the abnormality score of any current data is greater than the abnormality score threshold T5, the current data is abnormal data.

10. A data processing system for an integrated electronic control device, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a data processing method for an integrated electric control device according to any one of claims 1 to 9 is implemented.

Images