CN115636103B - Working condition separation method, device and equipment of PIU subsystem and storage medium - Google Patents
Working condition separation method, device and equipment of PIU subsystem and storage medium Download PDFInfo
- Publication number
- CN115636103B CN115636103B CN202211134703.4A CN202211134703A CN115636103B CN 115636103 B CN115636103 B CN 115636103B CN 202211134703 A CN202211134703 A CN 202211134703A CN 115636103 B CN115636103 B CN 115636103B
- Authority
- CN
- China
- Prior art keywords
- data
- working condition
- bus
- common
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000926 separation method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 79
- 230000001133 acceleration Effects 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000002776 aggregation Effects 0.000 claims abstract description 11
- 238000004220 aggregation Methods 0.000 claims abstract description 11
- 230000003247 decreasing effect Effects 0.000 claims description 39
- 238000005070 sampling Methods 0.000 claims description 20
- 238000005520 cutting process Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 description 13
- 230000010355 oscillation Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000013138 pruning Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a working condition separation method, device and equipment of a PIU subsystem and a storage medium, which solve the problem that the working condition separation method of the existing PIU subsystem is low in efficiency. The method comprises the following steps: acquiring bus data of a PIU subsystem, when the bus data are common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, and carrying out working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data; when the bus data are the accelerometer bus data, based on a preset second aggregation algorithm, working condition separation processing is carried out on the accelerometer bus data to obtain initial acceleration working condition data; and according to a second preset method, performing data jitter removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data. The PIU subsystem working condition separation method and device can improve the efficiency of the PIU subsystem working condition separation.
Description
Technical Field
The present invention relates to the field of data mining technologies, and in particular, to a method, an apparatus, a device, and a storage medium for separating working conditions of a PIU subsystem.
Background
Aircraft systems are a large and complex off-ground aircraft system, a most complex high-technology product of human manufacture. The PIU subsystem is a pilot control interface unit system and is mainly used for transmitting and displaying pilot operation instructions and airplane information. In the actual flight process, the operation conditions of various devices of the aircraft are changed continuously due to the changes of production conditions, environments, demands and the like, and the changes of the conditions become more complicated along with the increasing complexity of the aircraft system structure and the flight environment. Therefore, when the airplane is tested and subjected to fault diagnosis, faults and abnormal detection under various working condition modes are required to be realized, so that the safety and reliability of the airplane are improved, and the existing working condition separation method has the problem of low efficiency.
Disclosure of Invention
In view of this, the embodiments of the present invention provide a method, an apparatus, a device, and a storage medium for separating working conditions of a PIU subsystem, so as to solve the problem in the prior art that the method for separating working conditions of a PIU subsystem has low efficiency.
In order to solve the above technical problems, the present application provides a method for separating working conditions of a PIU subsystem, where the method includes:
obtaining bus data of a PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single frame data;
when the bus data are the common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, wherein single frame data of the first common bus data are discontinuously increased or continuously decreased;
according to a preset first clustering algorithm, carrying out working condition separation processing on the first common bus data to obtain initial common working condition data, wherein the initial common working condition data comprises highest bit data, lowest bit data and zero bit data;
when the bus data are the accelerometer bus data, based on a preset second clustering algorithm, working condition separation processing is carried out on the accelerometer bus data to obtain initial acceleration working condition data;
and according to a second preset method, performing data jitter removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data.
As some optional embodiments of the present application, the single frame data includes a removal tag, and when the bus data is the normal bus data, the step of preprocessing the normal bus data according to a first preset method to obtain first normal bus data includes:
traversing each single frame data of the common bus data to obtain a difference value between each single frame data and the single frame data of the previous frame;
when the difference value is larger than a preset difference value or the difference value is smaller than the opposite number of the preset difference value, adding the incremental pointer and setting the decremental pointer to zero, wherein the initial values of the incremental pointer and the decremental pointer are both 0;
when the difference value is smaller than a preset difference value or the difference value is larger than the opposite number of the preset difference value, setting the increment pointer to zero and adding one to the decrement pointer;
when the increment pointer is more than or equal to 3 or the decrement pointer is more than or equal to 3, the removal labels of the current single-frame data and the single-frame data of the previous 3 frames of the current single-frame data are set to be 1;
and removing all the single frame data with the removal tag of 1 to obtain first common bus data.
As some optional embodiments of the present application, the step of performing, according to a preset first clustering algorithm, working condition separation processing on the first common bus data to obtain initial common working condition data includes:
Acquiring a first aggregate reference distance according to a first preset distance dividing parameter and the extremely poor of the first common bus data;
creating a first working condition data set, wherein the first working condition data set comprises single frame data of a first frame in the first common bus data;
sequentially acquiring the difference value of the single frame data except the first frame in the first common bus data and the average value of the created first working condition data set;
when the difference value is larger than the first clustering reference distance, a first working condition data set is newly created, and corresponding single frame data is added into the newly created working condition data set;
when the difference value is smaller than or equal to the first clustering reference distance, adding the corresponding single frame data into the corresponding first working condition data set;
and obtaining initial common working condition data according to all the first working condition data sets.
As some optional embodiments of the present application, the step of obtaining initial common operating condition data according to all the first operating condition data sets includes:
acquiring average values and absolute value average values of all the first working condition data sets;
taking the first working condition data set with the maximum average value as the highest bit data;
Taking the first working condition data set with the minimum average value as the lowest-order data;
and taking the first working condition data set with the minimum absolute value average value as zero data.
As some optional embodiments of the present application, the single frame data includes a removal tag and an index tag, where the index tag corresponds to a frame number of the single frame data in the accelerometer bus data, and when the bus data is the accelerometer bus data, based on a preset second aggregation algorithm, the step of performing working condition separation processing on the accelerometer bus data to obtain initial acceleration working condition data includes:
setting the removal tag of single-frame data of which the continuous three frames are gradually increased or continuously three-vibration is gradually decreased in the accelerometer bus data to be 1;
acquiring a second convergence reference distance according to a second preset distance dividing parameter and the frame number of the accelerometer bus data;
creating a second working condition data set, wherein the second working condition data set comprises initial data, and the initial data is single frame data with the minimum index label in the single frame data with the removal label of 1;
traversing the single frame data which is not the initial data and has the removal label of 1 in the accelerometer bus data according to the index label, and obtaining the difference value of the index label of the single frame data and the index label of the single frame data of the previous frame;
When the difference value is smaller than or equal to the second aggregation reference distance, adding the corresponding single frame data into a second working condition data set corresponding to the previous single frame data;
when the difference value is larger than the second aggregation reference distance, a second working condition data set is recreated, and corresponding single frame data is added into the recreated second working condition data set;
calculating the upper and lower bounds of index labels of all the second working condition data sets;
setting the removal labels of the single frame data between the upper bound and the lower bound to be 1;
and eliminating the data with the removed tag of 1 to obtain initial acceleration working condition data.
As some optional embodiments of the present application, the performing, according to a second preset method, data jitter removal processing on the ordinary working condition data or the acceleration working condition data to obtain final ordinary working condition data or final acceleration working condition data includes:
sampling is carried out according to a preset sampling interval in the continuous preset number of single frame data of the initial common working condition data or the initial acceleration working condition data to obtain sampling data;
if the sampling data is increased or decreased, setting a removal tag corresponding to the sampling data to be 1;
Removing the data with the removed tag of 1 to obtain middle common working condition data or middle acceleration working condition data;
acquiring an index jump threshold value, a jump left clipping range and a jump right clipping range;
acquiring single frame data with index jump greater than the index jump threshold value in the middle common working condition data or the middle acceleration working condition data according to the index label, and marking the single frame data as jump data;
setting the removal labels of the single frame data in the jump left cutting range and the jump right cutting range of the jump data to 1;
and eliminating the data with the removed label of 1 to obtain final normal working condition data or final acceleration working condition data.
As some optional embodiments of the present application, the index jump threshold is 500-1000, and the left jump clipping range and the right jump clipping range are both 10-30.
For solving above-mentioned technical problem, this application still provides a PIU subsystem's operating mode separator, its characterized in that, the device includes:
the first acquisition module is used for acquiring bus data of the PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single-frame data;
The preprocessing module is used for preprocessing the common bus data according to a first preset method to obtain first common bus data when the bus data are the common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased;
the first working condition separation module is used for carrying out working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data, wherein the initial common working condition data comprises highest-order data, lowest-order data and zero-order data;
the second working condition separation module is used for carrying out working condition separation processing on the accelerometer bus data based on a preset second clustering algorithm when the bus data are the accelerometer bus data, so as to obtain initial acceleration working condition data;
and the data jitter removing module is used for carrying out data jitter removing processing on the initial common working condition data or the initial acceleration working condition data according to a second preset method to obtain final common working condition data or final acceleration working condition data.
In order to solve the above technical problem, the present application further provides an electronic device, including: at least one processor, at least one memory and computer program instructions stored in the memory, which when executed by the processor, implement the method as in the first aspect of the embodiments described above.
To solve the above technical problem, the present application further proposes a storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to the first aspect of the above embodiments.
In summary, the beneficial effects of the invention are as follows:
the application discloses a working condition separation method of a PIU subsystem, which comprises the steps of obtaining bus data of the PIU subsystem, wherein the bus data comprise common bus data and accelerometer bus data, and the common bus data comprise a plurality of single-frame data; when the bus data is the common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased, and due to the preprocessing, the single-frame data of the obtained first common bus data are discontinuously increased or continuously decreased, and data slope data are not suitable for any one of working condition data needing to be distinguished, and the speed of working condition separation can be improved and the efficiency can be improved by removing the data slope; according to a preset first clustering algorithm, working condition separation processing is carried out on the first common bus data to obtain initial common working condition data, wherein the initial common working condition data comprise highest-order data, lowest-order data and zero-order data, the clustering algorithm is an unsupervised algorithm, and the algorithm is simple and rapid and can further improve the working condition separation speed due to the fact that a training set is not needed; when the bus data is the accelerometer bus data, based on a preset second clustering algorithm, working condition separation processing is carried out on the accelerometer bus data to obtain initial acceleration working condition data, and as can be seen, the accelerometer bus data and the common bus data respectively pass through different clustering algorithms, so that the flexibility is high; and according to a second preset method, performing data shake removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described, and it is within the scope of the present invention to obtain other drawings according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for operating condition separation of a PIU subsystem according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a working condition separating device of a PIU subsystem according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely configured to illustrate the invention and are not configured to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the invention by showing examples of the invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The aircraft system is a complex engineering system and consists of a plurality of systems such as a navigation system, an electromechanical system, a flight control system, a power system, a communication system and the like. The PIU (Pilot-operation Interface Unit, power interface unit) subsystem is used for operating the interface unit subsystem for a Pilot in the field of aviation technology, and the subsystem can collect electric signals of key components in an aircraft system through an interface and convert the electric signals into digital signals through a bus network and transmit the digital signals to a computer to form test data.
However, based on a large amount of data obtained by airplane testing, most of existing airplane fault detection is performed in a single working condition mode, most of complex working conditions are generally integrated into a global model, and only a group of normal data relationships and ranges are used as the basis for judging whether the system is abnormal or not. Actual tests show that for the multi-working-condition aircraft system, the obtained normal test data under different working conditions are different. It can be seen that it is not suitable to use a single global model to detect anomalies in an aircraft system, and that parameter output deviation caused by conversion between different working conditions may affect anomaly determination, and may sacrifice sensitivity of anomaly detection for taking into account more working conditions. Therefore, aiming at the problems, the separation and the analysis of different working conditions are needed.
At present, some domestic researches adopt a clustering or statistical analysis method such as a k-means clustering algorithm, an SAGA algorithm, an FCM algorithm and the like to separate various working conditions. However, these methods are inefficient for large-scale data of aircraft systems and are not widely used, and further improvements are still needed.
In order to solve the above technical problems, the present application provides a method for separating working conditions of a PIU subsystem, where the method includes:
S1, acquiring bus data of a PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single-frame data;
specifically, firstly, bus data of a PIU subsystem is obtained, the bus data can be divided into two types according to the data working condition included in the bus data, namely common bus data and accelerometer bus data, wherein the common bus data comprises zero data, highest bit data and lowest bit data, in a specific embodiment, the common bus data comprises first common bus data, second common bus data and third common bus data, the first common bus data comprises lowest bit data and highest bit data, the second common bus data comprises zero data, lowest bit data and highest bit data, and the lowest bit data and the highest bit data are the same as the initial threshold absolute value of the highest bit data; the third common bus data comprises zero data, lowest-order data and highest-order data, wherein the initial threshold absolute values of the lowest-order data and the highest-order data are different; the accelerometer bus data are generated by each accelerometer experiment and comprise normal overload measurement highest data and axial and lateral overload side zero data, wherein the normal overload measurement highest data and the axial and lateral overload side zero data can be divided into two working conditions, namely a normal working condition and a shaking working condition, test data obtained under different working conditions are different, and it is obvious that a single global model is not suitable for detecting the abnormality of an aircraft system, and parameter output deviation caused by transformation between different working conditions can affect the judgment of the abnormality, so that the working conditions need to be separated.
S2, when the bus data are the common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased;
specifically, the data slope is a section of data with continuous data increasing or decreasing trend (the data slope is data slope with continuous increasing or decreasing trend with larger amplitude after being continuously increased (trend increasing) or decreasing trend after being temporarily decreased and becoming increasing trend) and continuously decreased with larger amplitude after being increased, the data slope is transition data from zero position working condition to highest (low) working condition or highest (low) working condition to zero position working condition, the data slope data is not any working condition needing to be distinguished and is interference data, and the data slope data is needed to be removed, so that the needed zero position working condition data, the highest working condition data and the lowest working condition data can be separated from the data of the data slope, in this step, the common bus data is preprocessed according to a first preset method to obtain the first common bus data, the single frame data of the first common bus data is not continuously increased or continuously decreased, the data slope is convenient to be removed, the jump information of the data slope is convenient to be analyzed by analyzing the jump information of the data, and the jump information of the data is relatively low, and the critical information is obtained.
As some optional embodiments of the present application, the single frame data includes a removal tag, and when the bus data is the normal bus data, the step of preprocessing the normal bus data according to a first preset method to obtain first normal bus data includes:
s21, traversing each single frame of data of the common bus data, and acquiring a difference value between each single frame of data and the single frame of data of the previous frame;
specifically, in order to remove a data slope in the common bus data, each single frame data in the common bus data needs to be traversed firstly to obtain a difference value between each single frame data and the single frame data of the previous frame, and the occurrence position of the data slope can be judged through the difference value, so that removal of the data slope is facilitated.
S22, adding an increasing pointer and setting a decreasing pointer to zero when the difference value is larger than a preset difference value or the difference value is smaller than the opposite number of the preset difference value, wherein the initial values of the increasing pointer and the decreasing pointer are both 0;
s23, when the difference value is smaller than a preset difference value or the difference value is larger than the opposite number of the preset difference value, setting the increment pointer to zero and adding one to the decrement pointer;
specifically, in order to realize the recognition of the data slope, an increasing pointer and a decreasing pointer are set, wherein initial values of the increasing pointer and the decreasing pointer are 0, when the difference value is smaller than a preset difference value or the difference value is larger than the opposite number of the preset difference value, the increasing pointer is set to zero and the decreasing pointer is increased by one, when the difference value is smaller than the preset difference value or the difference value is larger than the opposite number of the preset difference value, the increasing pointer is set to zero and the decreasing pointer is increased by one, the preset difference value is a positive number, and the determining can be performed according to the data characteristics of the bus data, and the specific limitation is not made here; by setting the increment pointer and the decrement pointer, the data slope can be quickly identified, and when the value of the increment pointer or the decrement pointer exceeds a preset pointer value, the data slope is indicated.
S24, when the increment pointer is more than or equal to 3 or the decrement pointer is more than or equal to 3, setting the removal labels of the current single-frame data and the single-frame data of the previous 3 frames of the current single-frame data to be 1;
specifically, in this embodiment, when the increment pointer or the decrement pointer is greater than or equal to 3, it is indicated that three continuous single frame data are incremented or decremented, and a data slope appears, three frames in the increment and decrement of three continuous single frame data are the minimum frame number showing that the data has an increment or decrement trend, the increment and decrement process of two continuous frames involves two frames of data and one increment or decrement, if the preset pointer value is adjusted to 2, the data of the non-data slope can be mistakenly removed, and the increment and decrement trend of the data can be clearly embodied, and the non-data slope data cannot be mistakenly removed, if the frame number is further increased, the omission and omission of the data slope can be caused, so in this step, when the increment pointer is greater than or equal to 3 or the decrement pointer is greater than or equal to 3, the removal labels of the current single frame data and the single frame data of the previous 3 frames of the current single frame data are all set to 1.
S25, removing all the single frame data with the removed tag being 1 to obtain first common bus data.
Specifically, in this step, all single frame data with the removal tag of 1 is removed to obtain first common bus data, and no single frame data with continuous increment or continuous decrement exists in the first common bus data, so that removal of a data slope is realized, and critical jump information such as a data jump degree, a data jump position and the like is conveniently obtained by analyzing less data information, thereby improving efficiency of parameter relevance analysis.
S3, carrying out working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data, wherein the initial common working condition data comprises highest-order data, lowest-order data and zero-order data;
specifically, a first clustering algorithm is preset at first, working condition separation processing is performed on the first common sub-line data to obtain initial common working condition data, the initial common working condition data comprises highest-order data, lowest-order data and zero-order data, the preset first clustering algorithm can comprise a K-means clustering algorithm, a density-based clustering algorithm, a grid-based clustering method and the like, the clustering algorithms are all in the prior art, the clustering algorithm is not repeated here, the clustering algorithm is an unsupervised algorithm, and because a training set is not needed, the algorithm is simple and rapid, and the working condition separation speed can be further improved.
As some optional embodiments of the present application, the step of performing, according to a preset first clustering algorithm, working condition separation processing on the first common bus data to obtain initial common working condition data includes:
s31, acquiring a first clustering reference distance according to a first preset distance dividing parameter and the extremely poor of the first common bus data;
specifically, a first clustering reference distance is obtained according to a first preset distance dividing parameter and the extremely poor of the first common bus data, and the first clustering reference distance is calculated by the following formula
Dist＝range/range_div
Wherein Dist is the first cluster reference distance, range is the extremely poor of the first common bus data, range_div is the first preset distance dividing parameter, the first preset distance dividing parameter can be set according to the actual situation by self setting, and in a specific embodiment, the value of the first preset distance dividing parameter is 5.
S32, creating a first working condition data set, wherein the first working condition data set comprises single frame data of a first frame in the first common bus data;
specifically, a first working condition data set is created first, single frame data of a first frame in the first common bus data is added into the first working condition data set to serve as initial data of the current first working condition data set, and comparison between single frame data except the single frame data of the first frame in a subsequent algorithm step and an average value of the first working condition data set is facilitated.
S33, sequentially acquiring a difference value of single frame data except a first frame in the first common bus data and an average value of the created first working condition data set;
s34, when the difference value is larger than the first clustering reference distance, a first working condition data set is newly created, and corresponding single frame data is added into the newly created working condition data set;
s35, when the difference value is smaller than or equal to the first clustering reference distance, adding the corresponding single frame data into the corresponding first working condition data set;
then, sequentially obtaining the difference value between the single frame data except the first frame in the first common bus data and the average value of the created first working condition data sets, namely sequentially comparing the single frame data of the second frame in the first common bus data with the average value of the created first working condition data sets to obtain the difference value, and when the difference value is larger than the first clustering reference distance, newly creating a first working condition data set and adding the corresponding single frame data into the newly created first working condition data set; when the difference value is smaller than or equal to the first clustering reference distance, adding the corresponding single frame data into the corresponding first working condition data set, and updating the average value of the corresponding first working condition data set; for example, firstly, obtaining the difference between the single frame data of the second frame and the average value of the first working condition data set 1, and recording the difference as a first difference, wherein the first working condition data set 1 comprises the single frame data of the first frame, the first difference is smaller than the first clustering reference distance, then the single frame data of the second frame is added into the first working condition data set 1, and the average value of the first working condition data set 1 is updated, then, obtaining the second difference between the single frame data of the third frame in the first common bus data and the updated average value, and the second difference is larger than the first clustering reference distance, then, creating a new first working condition data set 2, and adding the single frame data of the third frame into the first working condition data set 2 until all single frame data in the first common bus data are traversed;
S36, obtaining initial common working condition data according to all the first working condition data sets.
Specifically, different working condition data in the first common bus data are separated by a clustering method, in the separation process, the first common bus data are subjected to frame-by-frame comparison and continuous updating of the working condition data average value, clustering is achieved, and finally three data of a zero state, a highest bit state and a lowest bit state are separated from the first common bus data, so that a foundation is laid for subsequent multi-working condition fault diagnosis.
As some optional embodiments of the present application, the step of obtaining initial common operating condition data according to all the first operating condition data sets includes:
s361, obtaining average values and absolute value average values of all the first working condition data sets;
specifically, after each first working condition data set is obtained, the average value and the absolute value average value of each first working condition data set are obtained, and because single frame data in each first working condition data set are different working condition data, each first working condition data set can be judged to be the highest-order data, the lowest-order data or the zero-order data by the average value and the absolute value average value of each first working condition data set;
S362, taking the first working condition data set with the maximum average value as the highest bit data;
s363, using the first working condition data set with the minimum average value as the lowest-order data;
s364, taking the first working condition data set with the minimum absolute value average value as zero data.
Specifically, in each finally obtained first working condition data set, the first working condition data set with the smallest absolute value average value is data corresponding to a zero working condition, and is marked as zero data, the first working condition data set with the largest average value is data corresponding to a highest working condition, and is marked as highest data, and the first working condition data set with the smallest average value is data corresponding to a lowest working condition, and is marked as lowest data.
S4, when the bus data are the accelerometer bus data, carrying out working condition separation processing on the accelerometer bus data based on a preset second clustering algorithm to obtain initial acceleration working condition data;
specifically, when the bus data is the accelerometer bus data, based on a preset second clustering algorithm, working condition separation processing is performed on the accelerometer bus data to obtain initial acceleration working condition data, in this embodiment, the accelerometer bus data includes normal overload measurement highest-order data and axial and lateral overload side zero-order data, wherein the normal overload measurement highest-order data and the axial and lateral overload side zero-order data can be divided into two working conditions, a normal working condition and a shaking working condition, test data obtained under different working conditions are different, and initial acceleration working condition data obtained after working condition separation processing only includes data of the normal working condition, so that working condition separation of the accelerometer bus data is realized; and because the data characteristics of the accelerometer bus data and the common bus data are different, the accelerometer bus data are subjected to working condition separation processing by different clustering methods, and the flexibility of an algorithm is improved, so that the efficiency of bus data working condition separation is improved.
As some optional embodiments of the present application, the single frame data includes a removal tag and an index tag, where the index tag corresponds to a frame number of the single frame data in the accelerometer bus data, and when the bus data is the accelerometer bus data, based on a preset second aggregation algorithm, the step of performing working condition separation processing on the accelerometer bus data to obtain initial acceleration working condition data includes:
s41, setting the removal tag of single-frame data with continuous three-frame increment or continuous three-vibration decrement in the accelerometer bus data to be 1;
specifically, the data of the jitter working condition is formed by alternately increasing or decreasing data slopes in multiple sections, 3 frames in continuous 3-frame increasing and decreasing are the least frames showing the increasing or decreasing trend of the data, the continuous two-frame increasing and decreasing process involves two frames of data and one increasing or decreasing process, the one increasing and decreasing process is defined to be one oscillation immediately after one decreasing, one oscillation comprises one continuous two-frame increasing and one continuous two-frame decreasing process, multiple continuous oscillations exist in the non-data slopes of the data of the same working condition, if the data are adjusted to be 2 frames, the data of the normal working condition can be mistakenly removed, the increasing and decreasing trend of the data can be clearly shown by the 3-frame data, the non-data slope data cannot be mistakenly removed, and if the number of frames is further increased, the missing detection of the data slopes of the jitter working condition can be caused.
S42, obtaining a second polymerization reference distance according to a second preset distance dividing parameter and the frame number of the accelerometer bus data;
specifically, a second aggregate reference distance is obtained according to a second preset distance dividing parameter and the frame number of the accelerometer bus data, wherein the second aggregate reference distance is calculated by the following formula:
Len_dist＝Len/Len_div
wherein len_dist is the second convergence reference distance, len_div is the second preset distance dividing parameter, len is the number of frames of the accelerometer bus data, where the second preset distance dividing parameter may be set according to an actual situation, and in a specific embodiment, the second preset distance dividing parameter is 10.
S43, creating a second working condition data set, wherein the second working condition data set comprises initial data, and the initial data is the single frame data with the minimum index label in the single frame data with the removal label of 1;
specifically, a second working condition data set is firstly created, and single frame data with the minimum index label in single frame data with the label of 1 is removed from the accelerometer bus data to be used as initial data of the second working condition data set;
s44, traversing the single frame data which is not the initial data and has the removal label of 1 in the accelerometer bus data according to the index label, and obtaining a difference value of the index label of the single frame data and the index label of the single frame data of the previous frame;
S45, when the difference value is smaller than or equal to the second aggregation reference distance, adding the corresponding single frame data into a second working condition data set corresponding to the previous single frame data;
s46, when the difference value is larger than the second aggregation reference distance, a second working condition data set is recreated, and corresponding single frame data is added into the recreated second working condition data set;
then traversing the single frame data which is not the initial data and has the removal label of 1 in the accelerometer bus data according to the index label, obtaining the difference value of the index label of the single frame data and the single frame data of the previous frame, when the difference value is larger than the first clustering reference distance, newly creating a second working condition data set, and adding the corresponding single frame data into the newly created second working condition data set; when the difference value is smaller than or equal to the second aggregation reference distance, adding the corresponding single frame data into a second working condition data set corresponding to the previous single frame data;
s47, calculating the upper and lower bounds of index labels of all second working condition data sets;
s48, setting the removal labels of the single frame data between the upper bound and the lower bound to be 1;
and S49, eliminating the data with the removed tag being 1 to obtain initial acceleration working condition data.
After all the second working condition data sets are acquired, calculating the upper bound and the lower bound of the index label of each second working condition data set, wherein the upper bound is the maximum value of the index label of single-frame data in the second working condition data set, the lower bound is the minimum value of the index label of single-frame data in the second working condition data set, the removal label of the data between the upper bound and the lower bound is set to be 1, the data with the removal label of 1 is removed, the removal of the data of the shake working condition in the accelerometer bus data is realized, and the data of the normal working condition is reserved and integrated for algorithm.
And S5, according to a second preset method, performing data jitter removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data.
Specifically, after the ordinary bus data and the accelerometer bus data are separated under the primary working condition, the obtained initial ordinary working condition data or the initial acceleration working condition data have certain jitter at the position corresponding to the working condition conversion of the ordinary bus data and the accelerometer bus data, so that the initial ordinary working condition data or the initial acceleration working condition data are subjected to data jitter removal processing by a second preset method to obtain final ordinary working condition data or final acceleration working condition data so as to remove the data jitter of the initial ordinary working condition data or the initial acceleration working condition data,
As some optional embodiments of the present application, the performing, according to a second preset method, data jitter removal processing on the ordinary working condition data or the acceleration working condition data to obtain final ordinary working condition data or final acceleration working condition data includes:
s51, sampling is carried out according to a preset sampling interval in continuous single frame data of preset quantity of the initial normal working condition data or the initial acceleration working condition data to obtain sampling data;
specifically, in the first data ramp removal, a small amount of continuous single increment and single decrement alternate oscillation is present, the difference value between the partial data ramp data and the actual normal working condition data is less than 1/10 of the extremely bad total data, and the increment and decrement data trend still exists, so that sampling is performed according to a preset sampling interval in the continuous preset number of single frame data of the initial normal working condition data or the initial acceleration working condition data, so as to obtain sampling data;
s52, if the sampling data is increased or decreased, setting a removal tag corresponding to the sampling data to be 1;
s53, eliminating the data with the removed tag being 1 to obtain middle common working condition data or middle acceleration degree working condition data;
And then, if the sampling data is increased or decreased, setting a removal tag corresponding to the sampling data to be 1, removing the data with the removal tag of 1, and obtaining middle common working condition data or middle acceleration working condition data.
S54, acquiring an index jump threshold value, a jump left clipping range and a jump right clipping range;
specifically, firstly, an index jump threshold value, a jump left cutting range and a jump right cutting range are obtained, and values of the index jump threshold value, the jump left cutting range and the jump right cutting range can be set according to data characteristics;
in one embodiment, since the interval length between data of the same working condition type is the length of other data of the interval between two pieces of data belonging to the same working condition data type in the initial unprocessed data (and no working condition data of the type exists between the two pieces of data), when the interval length is greater than a certain extent, data oscillation with single increment and single decrement alternating is generated at the starting position and the ending position of a data slope of data working condition conversion, and the minimum value of the interval length for generating the oscillation is about 500-1000, and the minimum value can be called an index jump threshold value; however, the length of the oscillation data is not large, and the oscillation data is specifically located at a position where the index label jump of the single frame data is greater than the index jump threshold value by about 10-30 frames, as some optional embodiments of the application, the index jump threshold value is 500-1000, the jump left pruning range and the jump right pruning range are both 10-30, and in a preferred embodiment, the index jump threshold value is 500, and the jump left pruning range and the jump right pruning range are both 25.
S55, acquiring single frame data with index jump greater than the index jump threshold value in the middle common working condition data or the middle acceleration working condition data according to the index label, and marking the single frame data as jump data;
acquiring single frame data with index jump greater than the index jump threshold value in the middle common working condition data or the middle acceleration working condition data according to the index label, marking the single frame data as jump data, wherein the index jump is the difference value of the index label of the single frame data of the previous frame and the single frame data of the next frame, and marking the corresponding single frame data as jump data and recording the position of the jump data when the difference value is greater than the index jump threshold value;
s56, setting the removal labels of the single frame data in the jump left cutting range and the jump right cutting range of the jump data to be 1;
and S57, eliminating the data with the removed tag of 1 to obtain final common working condition data or final acceleration working condition data.
Specifically, after all the jump data are acquired, the removal labels of the single frame data in the jump left cutting range and the jump right cutting range of the jump data are set to be 1, and the single frame data with the removal labels of 1 are removed, so that the removal of data oscillation is realized, the obtained final normal working condition data or final acceleration working condition data are more accurate, in the data processing process, the data processing is realized through the index labels and the removal labels, the initial attribute of the data is not lost, and the accuracy of working condition separation is further improved.
In summary, according to the working condition separation method of the PIU subsystem, bus data of the PIU subsystem are obtained; when the bus data is the common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, wherein single frame data of the first common bus data are discontinuously increased or continuously decreased, so that the single frame data of the obtained first common bus data are discontinuously increased or continuously decreased, data slope data are not suitable for any one of working condition data which need to be distinguished, and the speed of working condition separation and the efficiency of working condition separation can be improved by removing the data slope; according to a preset first clustering algorithm, working condition separation processing is carried out on the first common bus data to obtain initial common working condition data, wherein the initial common working condition data comprise highest bit data, lowest bit data and zero bit data, the clustering algorithm is an unsupervised algorithm, and the algorithm is simple and rapid because a training set is not needed, and the working condition separation speed can be further improved; when the bus data are the accelerometer bus data, based on a preset second clustering algorithm, working condition separation processing is carried out on the accelerometer bus data to obtain initial acceleration working condition data, and the accelerometer bus data and the common bus data are respectively subjected to different clustering algorithms, so that the flexibility is high; and according to a second preset method, performing data jitter removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data.
In order to solve the above technical problem, referring to fig. 2, the present application further provides a working condition separating device of a PIU subsystem, where the device includes:
the first acquisition module is used for acquiring bus data of the PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single-frame data;
the preprocessing module is used for preprocessing the common bus data according to a first preset method to obtain first common bus data when the bus data are the common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased;
the first working condition separation module is used for carrying out working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data, wherein the initial common working condition data comprises highest-order data, lowest-order data and zero-order data;
the second working condition separation module is used for carrying out working condition separation processing on the accelerometer bus data based on a preset second clustering algorithm when the bus data are the accelerometer bus data, so as to obtain initial acceleration working condition data;
And the data jitter removing module is used for carrying out data jitter removing processing on the initial common working condition data or the initial acceleration working condition data according to a second preset method to obtain final common working condition data or final acceleration working condition data.
It should be noted that, each module in the working condition separating device of the PIU subsystem in this embodiment corresponds to each step in the working condition separating method of the PIU subsystem in the foregoing embodiment, so specific implementation manner and achieved technical effect of this embodiment may refer to implementation manner of the working condition separating method of the PIU subsystem, and will not be described herein again.
In addition, the method for separating the working conditions of the PIU subsystem according to the embodiment of the present invention described in connection with fig. 1 may be implemented by an electronic device. Fig. 3 shows a schematic hardware structure of an electronic device according to an embodiment of the present invention.
The electronic device may comprise at least one processor 301, at least one memory 302 and computer program instructions stored in the memory 302 that, when executed by the processor 301, implement the method described in the above embodiments.
In particular, the processor 301 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.
Memory 302 may include mass storage for data or instructions. By way of example, and not limitation, memory 302 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 302 may include removable or non-removable (or fixed) media, where appropriate. Memory 302 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In particular embodiments, memory 302 includes Read Only Memory (ROM). The ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these, where appropriate.
Processor 301 reads and executes the computer program instructions stored in memory 302 to implement any of the above-described methods of operating condition decoupling of the PIU subsystem.
In one example, the operating mode decoupling device of the PIU subsystem may also include a communication interface and a bus. As shown in fig. 3, the processor 301, the memory 302, and the communication interface 303 are connected to each other by a bus 310 and perform communication with each other. The communication interface is mainly used for realizing communication among the modules, the devices, the units and/or the equipment in the embodiment of the invention.
The bus includes hardware, software, or both, that couple components of the operating mode separating device of the PIU subsystem to each other. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of these. The bus may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
In addition, in combination with the method for separating the working conditions of the PIU subsystem in the above embodiment, the embodiment of the invention may be implemented by providing a computer readable storage medium. The computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by the processor, implement a method for operating condition separation for any of the PIU subsystems of the embodiments described above.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.
Claims (10)
1. A method for operating condition separation of a PIU subsystem, the method comprising:
acquiring bus data of a PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single frame data;
When the bus data are the common bus data, preprocessing the common bus data according to a first preset method to obtain first common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased;
according to a preset first clustering algorithm, carrying out working condition separation processing on the first common bus data to obtain initial common working condition data, wherein the initial common working condition data comprises highest-order data, lowest-order data and zero-order data;
when the bus data are the accelerometer bus data, based on a preset second clustering algorithm, working condition separation processing is carried out on the accelerometer bus data to obtain initial acceleration working condition data;
and according to a second preset method, performing data jitter removal processing on the initial normal working condition data or the initial acceleration working condition data to obtain final normal working condition data or final acceleration working condition data.
2. The method for separating the working conditions of the PIU subsystem according to claim 1, wherein the single frame data includes a removal tag, and the step of preprocessing the normal bus data according to a first preset method to obtain first normal bus data when the bus data is the normal bus data includes:
Traversing each single frame data of the common bus data to obtain a difference value between each single frame data and the single frame data of the previous frame;
when the difference value is larger than a preset difference value or the difference value is smaller than the opposite number of the preset difference value, adding an increasing pointer and setting a decreasing pointer to zero, wherein the initial values of the increasing pointer and the decreasing pointer are 0;
when the difference value is smaller than a preset difference value or the difference value is larger than the opposite number of the preset difference value, setting the increment pointer to zero and adding one to the decrement pointer;
when the increment pointer is more than or equal to 3 or the decrement pointer is more than or equal to 3, the removal labels of the current single-frame data and the single-frame data of the previous 3 frames of the current single-frame data are set to be 1;
and removing all the single frame data with the removal tag of 1 to obtain first common bus data.
3. The method for separating the working conditions of the PIU subsystem according to claim 1, wherein the step of performing working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data includes:
acquiring a first clustering reference distance according to a first preset distance dividing parameter and the extremely poor of the first common bus data;
Creating a first working condition data set, wherein the first working condition data set comprises single frame data of a first frame in the first common bus data;
sequentially acquiring the difference value of the single frame data except the first frame in the first common bus data and the average value of the created first working condition data set;
when the difference value is smaller than or equal to the first clustering reference distance, adding the corresponding single frame data into a first working condition data set;
when the difference value is larger than the first clustering reference distance, a first working condition data set is newly created, and corresponding single frame data is added into the newly created working condition data set;
and obtaining initial common working condition data according to all the first working condition data sets.
4. A method of operating condition separation for a PIU subsystem according to claim 3, wherein the step of obtaining initial common operating condition data from all of the first operating condition data sets comprises:
acquiring average values and absolute value average values of all the first working condition data sets;
taking the first working condition data set with the maximum average value as the highest bit data;
taking the first working condition data set with the minimum average value as the lowest-order data;
and taking the first working condition data set with the minimum absolute value average value as zero data.
5. The method for operating condition separation of a PIU subsystem according to claim 1, wherein the single frame data includes a removal tag and an index tag, the index tag corresponds to a frame number of the single frame data in the accelerometer bus data, and when the bus data is the accelerometer bus data, the step of performing operating condition separation processing on the accelerometer bus data based on a preset second clustering algorithm to obtain initial acceleration operating condition data includes:
setting the removal tag of single-frame data of which three continuous frames are increased or three continuous frames are decreased in the accelerometer bus data to be 1;
acquiring a second convergence reference distance according to a second preset distance dividing parameter and the frame number of the accelerometer bus data;
creating a second working condition data set, wherein the second working condition data set comprises initial data, and the initial data is single frame data with the minimum index label in the single frame data with the removal label of 1;
traversing the single frame data which is not the initial data and has the removal label of 1 in the accelerometer bus data according to the index label, and obtaining the difference value of the index label of the single frame data and the index label of the single frame data of the previous frame;
When the difference value is smaller than or equal to the second aggregation reference distance, adding the corresponding single frame data into a second working condition data set corresponding to the previous single frame data;
when the difference value is larger than the second aggregation reference distance, a second working condition data set is recreated, and corresponding single frame data is added into the recreated second working condition data set;
calculating the upper and lower bounds of index labels of all the second working condition data sets;
setting the removal labels of the single frame data between the upper bound and the lower bound to be 1;
and eliminating the data with the removed tag of 1 to obtain initial acceleration working condition data.
6. The method for separating the working conditions of the PIU subsystem according to claim 5, wherein the performing data jitter removal processing on the common working condition data or the acceleration working condition data according to the second preset method to obtain final common working condition data or final acceleration working condition data includes:
sampling is carried out according to a preset sampling interval in the continuous preset number of single frame data of the initial common working condition data or the initial acceleration working condition data to obtain sampling data;
if the sampling data is increased or decreased, setting a removal tag corresponding to the sampling data to be 1;
Removing the data with the removed tag of 1 to obtain middle common working condition data or middle acceleration working condition data;
acquiring an index jump threshold value, a jump left clipping range and a jump right clipping range;
acquiring single frame data with index jump greater than the index jump threshold value in the middle common working condition data or the middle acceleration working condition data according to the index label, and marking the single frame data as jump data;
setting the removal labels of single frame data in the jump left cutting range and the jump right cutting range of the jump data to 1;
and eliminating the data with the removed tag of 1 to obtain final common working condition data or final acceleration working condition data.
7. The method for separating the PIU subsystem according to claim 6, wherein the index jump threshold is 500-100, and the left jump clipping range and the right jump clipping range are both 10-30.
8. A condition decoupling device for a PIU subsystem, the device comprising:
the first acquisition module is used for acquiring bus data of the PIU subsystem, wherein the bus data comprises common bus data and accelerometer bus data, and the common bus data comprises a plurality of single-frame data;
The preprocessing module is used for preprocessing the common bus data according to a first preset method to obtain first common bus data when the bus data are the common bus data, wherein single-frame data of the first common bus data are discontinuously increased or continuously decreased;
the first working condition separation module is used for carrying out working condition separation processing on the first common bus data according to a preset first clustering algorithm to obtain initial common working condition data, wherein the initial common working condition data comprises highest-order data, lowest-order data and zero-order data;
the second working condition separation module is used for carrying out working condition separation processing on the accelerometer bus data based on a preset second aggregation algorithm when the bus data are the accelerometer bus data, so as to obtain initial acceleration working condition data;
and the data jitter removing module is used for carrying out data jitter removing processing on the initial common working condition data or the initial acceleration working condition data according to a second preset method to obtain final common working condition data or final acceleration working condition data.
9. An electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of any one of claims 1-7.
10. A storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211134703.4A CN115636103B (en) | 2022-09-19 | 2022-09-19 | Working condition separation method, device and equipment of PIU subsystem and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211134703.4A CN115636103B (en) | 2022-09-19 | 2022-09-19 | Working condition separation method, device and equipment of PIU subsystem and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115636103A CN115636103A (en) | 2023-01-24 |
| CN115636103B true CN115636103B (en) | 2024-03-15 |
Family
ID=84941701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211134703.4A Active CN115636103B (en) | 2022-09-19 | 2022-09-19 | Working condition separation method, device and equipment of PIU subsystem and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115636103B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7272527B1 (en) * | 2006-03-30 | 2007-09-18 | Fujitsu Limited | Method of test of clock generation circuit in electronic device, and electronic device |
| CN112784266A (en) * | 2019-11-07 | 2021-05-11 | 泰勒斯公司 | Method and electronic device for monitoring an avionics software application, associated computer program and avionics system |
| CN113449703A (en) * | 2021-08-31 | 2021-09-28 | 天津联图科技有限公司 | Quality control method and device for environment online monitoring data, storage medium and equipment |
| CN114372489A (en) * | 2021-12-20 | 2022-04-19 | 中国北方发动机研究所(天津) | Diesel engine working condition identification and abnormity diagnosis method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170293517A1 (en) * | 2016-04-11 | 2017-10-12 | Simmonds Precision Products, Inc. | Physical component predicted remaining useful life |
-
2022
- 2022-09-19 CN CN202211134703.4A patent/CN115636103B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7272527B1 (en) * | 2006-03-30 | 2007-09-18 | Fujitsu Limited | Method of test of clock generation circuit in electronic device, and electronic device |
| CN112784266A (en) * | 2019-11-07 | 2021-05-11 | 泰勒斯公司 | Method and electronic device for monitoring an avionics software application, associated computer program and avionics system |
| CN113449703A (en) * | 2021-08-31 | 2021-09-28 | 天津联图科技有限公司 | Quality control method and device for environment online monitoring data, storage medium and equipment |
| CN114372489A (en) * | 2021-12-20 | 2022-04-19 | 中国北方发动机研究所(天津) | Diesel engine working condition identification and abnormity diagnosis method |
Non-Patent Citations (2)
| Title |
|---|
| 基于DSP的飞行数据采集装置的设计与实现;肖刚;卢京潮;;测控技术(第05期);43-45 * |
| 飞行器神经元控制系统的研究与设计;阮晓钢, 郭锁凤;航空学报(第02期);177-184 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115636103A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110018670A (en) | A kind of industrial process unusual service condition prediction technique excavated based on dynamic association rules | |
| CN109324604B (en) | Intelligent train comprehensive fault analysis method based on multi-source signals | |
| CN109489977B (en) | KNN-AdaBoost-based bearing fault diagnosis method | |
| US20070239629A1 (en) | Cluster Trending Method for Abnormal Events Detection | |
| CN114993669B (en) | Multi-sensor information fusion transmission system fault diagnosis method and system | |
| CN114167838B (en) | Multi-scale health assessment and fault prediction method for servo system | |
| CN113344134A (en) | Data acquisition abnormity detection method and system for low-voltage power distribution monitoring terminal | |
| CN109428647B (en) | Method, device and storage medium for realizing fault cause positioning | |
| CN110474862B (en) | Network traffic anomaly detection method and device | |
| CN115186762A (en) | Engine abnormity detection method and system based on DTW-KNN algorithm | |
| CN113526282A (en) | Method, device, medium and equipment for diagnosing medium and long-term aging faults of elevator | |
| CN115636103B (en) | Working condition separation method, device and equipment of PIU subsystem and storage medium | |
| CN109145764B (en) | Method and device for identifying unaligned sections of multiple groups of detection waveforms of comprehensive detection vehicle | |
| US11378944B2 (en) | System analysis method, system analysis apparatus, and program | |
| CN112528227A (en) | Sensor abnormal data identification method based on mathematical statistics | |
| CN113255771B (en) | Fault diagnosis method and system based on multi-dimensional heterogeneous difference analysis | |
| KR101575204B1 (en) | Apparatus and method for diagnosing a partial discharging equipped | |
| CN115392812A (en) | Abnormal root cause positioning method, device, equipment and medium | |
| CN112083707A (en) | Industrial control physical signal processing method, controller and processing system | |
| CN113075547A (en) | Motor data acquisition method and system | |
| CN115543667A (en) | Parameter relevance analysis method, device, equipment and medium for PIU subsystem | |
| CN111368782A (en) | Training method of coal fire area identification model, and coal fire area identification method and device | |
| CN114444623B (en) | Industrial robot-oriented anomaly detection and analysis method and system | |
| CN114757455B (en) | Trench trolley abnormity prediction method and system based on servo motor time sequence data | |
| CN113740345B (en) | Burr detection method and system under high-speed sampling rate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |