CN116609440B - Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation - Google Patents
Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation Download PDFInfo
- Publication number
- CN116609440B CN116609440B CN202310577867.2A CN202310577867A CN116609440B CN 116609440 B CN116609440 B CN 116609440B CN 202310577867 A CN202310577867 A CN 202310577867A CN 116609440 B CN116609440 B CN 116609440B
- Authority
- CN
- China
- Prior art keywords
- signal
- segment
- amplitude
- moment
- imf component
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 64
- 230000005236 sound signal Effects 0.000 claims abstract description 52
- 230000005856 abnormality Effects 0.000 claims abstract description 39
- 230000014759 maintenance of location Effects 0.000 claims abstract description 31
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000010276 construction Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 11
- 238000013450 outlier detection Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 7
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4454—Signal recognition, e.g. specific values or portions, signal events, signatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/48—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by amplitude comparison
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Immunology (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a cloud-edge collaboration-based intelligent acceptance management method and system for building engineering quality, comprising the following steps: EMD decomposition is carried out on the collected sound signals; segmenting the data characteristics of each segment according to each IMF component signal, and analyzing to obtain the noise retention degree; obtaining fluctuation degree weight according to the noise maintenance degree; acquiring a COF abnormal outlier factor and combining fluctuation degree weight to acquire signal abnormality degree at each moment; and carrying out abnormality identification according to the abnormality degree of the signal. According to the invention, the noise sound degree held in the sound signal in each component after EMD decomposition is used as the weight of the abnormal outlier factor obtained by the conventional COF algorithm, the weight summation is carried out, the COF algorithm is carried out to detect the abnormal signal, the interference of environmental noise is greatly reduced, and the recognition accuracy of the abnormal signal is increased.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a cloud-edge collaboration-based intelligent acceptance management method and system for construction engineering quality.
Background
In recent years, with the rapid development of cloud computing technology, intelligent acceptance management systems for building engineering quality are widely used gradually, and by integrating various technical means, the building engineering quality condition is monitored in real time and accurately evaluated. Whether the equipment is normally operated or not can have a small influence on the quality and efficiency of the construction engineering, and for such anomalies, the abnormal sounds caused by machine faults or construction errors which are more existing in the construction site are generally identified and monitored, equipment is replaced or construction details are checked in time, and the monitoring of the abnormal sound data is generally based on the identification of the abnormal sound data by a COF algorithm. However, in the conventional COF algorithm, a fixed K neighborhood range is set, and after an anomaly factor is calculated for data in the K neighborhood range corresponding to each data, a threshold value is set for the data, and then whether the data is anomalous data is determined. However, in the construction site environment, besides abnormal sounds caused by machine equipment, various noisy or noise signals exist, and fluctuation caused by noise data at each moment may be abnormal sounds of individual equipment or sound signals obtained by overlapping noise and equipment abnormality, so that a fixed threshold value often cannot achieve a good monitoring effect.
Disclosure of Invention
The invention provides a Yun Bian cooperation-based intelligent acceptance management method and system for construction engineering quality, which are used for solving the existing problems.
The invention discloses a Yun Bian cooperation-based intelligent acceptance management method and system for building engineering quality, which adopts the following technical scheme:
in one aspect, an embodiment of the invention provides a cloud-edge collaboration-based intelligent acceptance management method for building engineering quality, which comprises the following steps:
collecting a sound signal of the whole day on a construction site, preprocessing the sound signal to obtain an initial signal, and carrying out EMD (empirical mode decomposition) according to the initial signal to obtain a plurality of IMF (intrinsic mode function) component signals;
segmenting according to the initial signal and the moments of all IMF component signals to obtain each segment of each signal;
obtaining amplitude fluctuation values of signal amplitudes at all moments in each segment according to each segment of the initial signal;
acquiring signal difference of an initial signal and a component signal at each moment in each segment, marking the signal difference as a first signal difference value, obtaining a confidence coefficient characteristic at each moment in each segment according to the signal difference of the component signal at the adjacent moment in each segment, and obtaining an integral numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic at each moment;
obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal;
obtaining fluctuation degree weights according to the noise retention degrees of all the segments in each IMF component signal, and obtaining signal abnormality degrees at each moment according to COF abnormality outlier factors and the fluctuation degree weights obtained by calculation in each IMF component signal at each moment;
and judging an abnormal signal according to the abnormal degree of each moment and obtaining corresponding abnormal equipment.
Preferably, the segmentation is performed according to the time of the initial signal and all IMF component signals to obtain each signal
The segmentation comprises the following specific steps:
and segmenting the signals according to time according to the obtained initial signals and all IMF component signals, and dividing all signals comprising the initial signals and all IMF component signals into a plurality of segments according to a fixed segment size to obtain each segment of each signal.
Preferably, the amplitude fluctuation of the signal amplitude at all moments in each segment is obtained from each segment of the initial signal
The values include the following specific steps:
the method comprises the steps of obtaining the amplitude of each moment in each segment in an initial signal, and obtaining the calculation formula of the amplitude fluctuation value of the signal amplitude at all moments in each segment according to the segments, the moment and the signal amplitude, wherein the calculation formula is as follows:
wherein ε m Is the amplitude fluctuation value of the signal amplitude at all moments in the mth segment of the initial signal, M is the total number of all segments in each signal, M is the label of a segment in all segments of the initial signal and has M E [1, M]T is the number of instants contained in each segment of the initial signal, T is the index of a certain instant contained in each segment of the initial signal and has t.epsilon.1, T]，a mt Is the signal amplitude at time t in the mth segment of the initial signal,is the arithmetic mean of the signal amplitudes at all times in the mth segment in the initial signal, exp () is an exponential function with a base of natural constant.
Preferably, the acquiring the signal difference between the initial signal and the component signal at each moment in each segment is recorded as a first signal difference value, and the confidence coefficient feature at each moment in each segment is obtained according to the signal difference between the component signal at adjacent moments in each segment, including the following specific steps:
acquiring a signal amplitude of each moment in each segment in each IMF component signal, normalizing the signal amplitude of each moment in each segment in an initial signal to obtain a first amplitude, normalizing the signal amplitude of the same moment in the same segment in each IMF component signal to obtain a second amplitude, taking a difference between the first amplitude and the second amplitude and taking an absolute value to obtain a signal difference of each moment in each segment, and marking the signal difference of each moment in each segment as a first signal difference value; meanwhile, the signal amplitude of each moment in each IMF component signal except a certain IMF component signal is obtained and marked as a third amplitude, the signal amplitude of the previous moment in each moment except the certain IMF component signal is obtained and marked as a fourth amplitude, the difference is made according to the third amplitude and the fourth amplitude, the absolute value is summed and divided by the quantity of IMF component signals obtained by carrying out EMD decomposition on the initial signal, and the confidence characteristic of each moment is obtained.
Preferably, the step of obtaining the overall numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient feature of each time in each segment includes the following specific steps:
and multiplying and accumulating according to the first signal difference value and the confidence coefficient characteristic of each moment in each segment to obtain the integral numerical proportion difference value existing in each segment in each IMF component signal.
Preferably, the calculation formula for obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion size difference value existing in each segment in each IMF component signal is as follows:
wherein C is n Is the noise retention level of all segments in the nth IMF component signal, M is the total number of all segments in each signal, μ mn Is the overall numerical scale magnitude difference value present in the mth segment in the nth IMF component signal,is the arithmetic mean, epsilon, of the overall numerical scale magnitude differences present in all M segments in the nth IMF component signal m Is the amplitude fluctuation value of the signal amplitude at all times in the initial signal of the mth segment, norm (ε) m ) Amplitude fluctuation value epsilon representing signal amplitude at all times of mth segment in initial signal m And (5) performing linear normalization operation.
Preferably, the step of obtaining the fluctuation degree weight according to the noise retention degree of all the segments in each IMF component signal, and obtaining the signal abnormality degree at each moment according to the COF abnormality outlier factor and the fluctuation degree weight calculated in each IMF component signal at each moment includes the following specific steps:
and carrying out conventional COF outlier detection according to the signal at each moment under each IMF component to obtain a COF outlier factor of each moment in each IMF component signal, normalizing according to the noise retention degree of all the segments in each IMF component signal to obtain a fluctuation degree weight, and multiplying and accumulating the COF outlier factor and the fluctuation degree weight of each moment in each IMF component signal to obtain the signal abnormality degree of each moment.
On the other hand, one embodiment of the invention provides a cloud-edge collaboration-based intelligent acceptance management system for the quality of construction engineering, which comprises the following modules:
and a data acquisition module: the method is used for collecting sound signals of the whole day on the site;
and a data processing module: the method comprises the steps of preprocessing a sound signal to obtain an initial signal, and carrying out EMD (empirical mode decomposition) according to the initial signal to obtain a plurality of IMF (intrinsic mode function) component signals; segmenting according to the initial signal and the moments of all IMF component signals to obtain each segment of each signal; obtaining amplitude fluctuation values of signal amplitudes at all moments in each segment according to each segment of the initial signal; acquiring signal difference of an initial signal and a component signal at each moment in each segment, marking the signal difference as a first signal difference value, obtaining a confidence coefficient characteristic at each moment in each segment according to the signal difference of the component signal at the adjacent moment in each segment, and obtaining an integral numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic at each moment; obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal; obtaining fluctuation degree weights according to the noise retention degrees of all the segments in each IMF component signal, and obtaining signal abnormality degrees at each moment according to COF abnormality outlier factors and the fluctuation degree weights obtained by calculation in each IMF component signal at each moment;
the abnormality judgment module: and the equipment is used for judging the abnormal signal according to the abnormal degree of each moment and obtaining the corresponding abnormal occurrence.
The technical scheme of the invention has the beneficial effects that: when abnormal sound identification is performed through a conventional COF algorithm, noise signals inevitably exist in a scene, so that characteristics such as frequency amplitude and the like of sound generated by abnormal equipment are weakened, and inaccurate detection is caused. The invention combines the basic knowledge that the sound of the abnormal equipment mainly exists in a certain frequency range, carries out EMD decomposition on the collected sound signals, takes the degree of noise sound degree held in the sound signals in each component after the decomposition as the degree of the abnormal equipment sound in each component, takes the degree as the degree of the abnormal equipment sound in the sound signals in the same moment in a plurality of IMF components, carries out weighted summation on abnormal outlier factors obtained by a conventional COF algorithm, and greatly reduces the interference of environmental noise, thereby increasing the recognition accuracy of the abnormal sound.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of the intelligent acceptance management method for the quality of the building engineering based on cloud edge cooperation.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof, which are based on cloud-edge collaboration, of the intelligent acceptance management method and system for construction engineering quality, which are provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a cloud-edge-collaboration-based intelligent acceptance management method and system for construction engineering quality, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a cloud-edge collaboration-based intelligent acceptance management method for quality of construction engineering according to an embodiment of the present invention is shown, where the method includes the following steps:
step S001: and acquiring a sound signal of the whole day on the site, preprocessing the sound signal to obtain an initial signal, and carrying out EMD (empirical mode decomposition) according to the initial signal to obtain N IMF component signals.
The edge computing device is installed, and comprises a sound sensor and a computing unit, wherein the sound sensor is used for acquiring sound signals of the whole day on a construction scene, and transmitting the sound signals of the whole day on the construction scene to the computing unit. And (3) performing data cleaning in the computing unit according to the acquired sound signals of the whole day on the site to remove possible sensor interference signals in the sound signals of the whole day on the site to obtain initial signals, wherein the cleaning in the embodiment is to perform smoothing processing on the data by using Gaussian filtering operation so that the obtained signals have fewer excessively abnormal signal values during processing. EMD decomposition is carried out according to the initial signals, and N IMF component signals are obtained. It should be noted that, in this embodiment, all signal expression modes are two-dimensional signal curves with the sensor sampling time t as the abscissa and the signal amplitude a as the ordinate. The sensor sampling time is an accumulated value of signal sampling intervals, and is a public cognition, and redundant description is omitted in this embodiment. Unless otherwise specified, all time concepts in the following description in this embodiment refer to the sensor sampling time.
Thus, initial signals and N IMF component signals are obtained according to acquired sound signals of the construction site for one whole day.
Step S002: and segmenting according to the time of the initial signal and all IMF component signals to obtain each segment of each signal.
According to the method, signals are segmented according to time according to the obtained initial signals and all IMF component signals, and all signals comprising the initial signals and all IMF component signals are divided into M segments according to a fixed segment size. The segment sizes in all signals are the same, and segments are performed by default from the zero time point (i.e., the signal abscissa zero point) of all signals. In this embodiment, the segment size is illustrated with a segment size of 20min, and the segment size may actually be changed according to different construction scenarios, and when the last segment is less than 20min, the signal with the remaining time sequence length is used as the last segment.
To this end, each segment of each signal is obtained by segmentation from the time instants of the initial signal and all IMF component signals.
Step S003: and obtaining the amplitude fluctuation value of the signal amplitude at all moments in each segment according to each segment of the initial signal.
The signal amplitude of each moment in each segment in the initial signal is calculated according to each segment in the initial signal to obtain the amplitude fluctuation value of the signal amplitude of all moments in each segment, and the formula is as follows:
wherein ε m Is the amplitude fluctuation value of the signal amplitude at all moments in the mth segment of the initial signal, M is the label of the segment in the M segments of the initial signal and has M E [1, M]M is the total number of all segments in each signal, T is the number of instants contained in each segment in the initial signal, T is the index of the instants contained in each segment in the initial signal and has tε [1, T]，a mt Is the signal amplitude at time t in the mth segment of the initial signal,is the arithmetic mean of the signal amplitudes at all times in the mth segment in the initial signal. exp (-a) my ) The signal amplitude at the t time in the mth segment in the initial signal is normalized, so that the signal amplitude of each time signal is given different weight sizes in the interval of [0,1 ] and along with a when the standard deviation is calculated mt And decreases with increasing numbers. It should be noted that, in this embodiment, the exp (-x) model is only used to indicate that the result output by the negative correlation and constraint model is in the [0,1 ] interval, and other models with the same purpose may be replaced in the implementation. Considering that the abnormal sound caused by the abnormality of the device required in the present embodiment is larger in amplitude and smaller in frequency than the other disturbing sounds, the noise holding degree in the subsequent step can be given a weight value according to the amplitude fluctuation value of the signal amplitude at a certain time.
To this end, the amplitude fluctuation value of the signal amplitude at all times in each segment is obtained from each segment of the initial signal.
Step S004: and obtaining a first signal difference value and a confidence coefficient characteristic of each moment in each section according to each section of each IMF component signal, and obtaining an integral numerical proportion difference value existing in each section of each IMF component signal according to the first signal difference value and the confidence coefficient characteristic of each moment in each section.
Since the existence of the device abnormality sound signal in the signal at each time in each section cannot be explained completely from the amplitude fluctuation value of the signal amplitude at each time in each section, the logic is because the amplitude fluctuation value of the signal amplitude at each time in each section is affected by the superposition of the disturbance between the ambient sound and the noise signal, the IMF component signal of the device abnormality sound signal also has the influence of the partial noise signal, and the influence of the certain similarity between the noise signals, the existence of the device abnormality sound signal in the signal at each time in each section cannot be explained singly. The present embodiment regards the noise signal as a normal signal, thereby evaluating the degree to which the amplitude of the noise signal is maintained in each segment, and thus deducing that there may be an abnormal sound signal of the device. The present embodiment thus performs an analytical evaluation of the normal noise signal characteristics for the signal amplitude at each time instant in each segment of each IMF component signal.
First, the present embodiment obtains the first signal difference value by calculating the signal difference between the signal amplitude at each time point in each segment of each IMF component signal and the signal amplitude in the initial signal at the same time point as follows:
A mnt ＝|norm(a mnt )-norm(a mt )|
wherein A is mnt Is the normalized signal difference of two amplitudes at the t-th moment in the m-th section of the nth IMF component signal, namely the first signal difference value, a mnt Is the signal amplitude at the time t in the mth segment of the nth IMF component signal, norm (a) mnt ) Represents a first amplitude obtained by linearly normalizing the signal amplitude at the t-th time in the mth segment of the nth IMF component signal, norm (a) mt ) The second amplitude obtained by linearly normalizing the signal amplitude at the t-th moment in the mth segment in the initial signal is represented, and the ratio of the signal amplitude at each moment in each segment of each IMF component signal to the signal amplitude value in the initial signal at the same moment is represented. When the magnitude of the ratio of the signal amplitude at each time instant in each segment of each IMF component signal to the signal amplitude value in the initial signal at the same time instant is greater, the greater the number of different signals present in the initial signal at that time instant is characterized. In a construction scene, the noise sound signal mainly consists of a noisy sound signal, the distance between the noisy sound signal and most of devices and the size difference of the corresponding sound signals are not too large, and the amplitude of the noise sound signal is usually large. However, since the amplitude of the abnormal signal caused by the abnormal device is usually large, when the abnormal sound signal of the device exists in the signal corresponding to a certain moment of a certain section of the IMF component signal, the duty ratio corresponding to the amplitude of the rest of the signals in the section is different, so thatAnd the obtained record is relatively large when the numerical ratio difference calculation is carried out. Meanwhile, it can be known that when the difference between the initial signal and the IMF component signal at a certain moment is larger, the certain sound signal in the initial signal at the moment occupies larger space, but the amplitude of the sound signal is not shown due to superposition of various sounds, so that after EMD decomposition, the amplitude of the certain sound signal in the initial signal at the moment can be disassembled, and the amplitude characteristic of the certain sound signal in the initial signal at the moment is obvious. Therefore, the amplitude values before and after the decomposition of the initial signal at this time are different from each other. This difference characterizes whether the sound at this moment is caused by superposition of sound signals of several different frequencies.
Thus, a first signal difference value is obtained by calculating the signal difference between the signal amplitude at each time instant in each segment of each IMF component signal and the signal amplitude in the initial signal at the same time instant.
Secondly, because the noise signal is caused by a noisy environment, the composition is complex, and even if the signal at some time does not have the abnormal sound signal of the device, the amplitude at some time is almost distributed under a certain IMF component signal, and the abnormal sound signal of the device is short but has a duration, so that additional adjustment is needed to avoid the interference of the extreme situations. Therefore, according to the present embodiment, the following formula is used for obtaining the confidence characteristic of each time in each segment according to the difference between the signal amplitude of each time in each segment of all IMF component signals except for a certain IMF component signal and the signal amplitude of the previous time in each segment of all IMF component signals except for a certain IMF component signal:
wherein k is mnt Is the confidence characteristic of the nth moment in m segments in the nth IMF component signal, namely the confidence characteristic of each moment in each segment,n is the number of IMF component signals, N 'is the total number of remaining IMF component signals excluding the nth IMF component signal, N' is the label of the remaining IMF component signals excluding the nth IMF component signal, N 'e [1, N ]']，a mn't ,a mn'(t-1) The third and fourth amplitudes are the signal amplitudes at the time point t and the time point (t-1) in the nth IMF component signal, that is, the signal amplitudes at the previous time point, except the nth IMF component signal. That is, when the amplitude variation of the remaining IMF component signals excluding the nth IMF component signal is larger, the probability that the difference in the numerical proportion of the nth IMF component signal is mainly due to abnormality in current amplitude allocation caused by complexity of noise composition components is smaller, and the confidence that the difference in the signal amplitude at each time in each of the sections of all IMF component signals except for a certain IMF component signal and the signal amplitude at the previous time in each of the sections of all IMF component signals except for a certain IMF component signal is not extreme case interference is lower. In order to avoid unreasonable time when t-1=0 occurs, in the process of calculating the confidence coefficient feature of the nth time in the m segments in the nth IMF component signal in this embodiment, the confidence coefficient feature of the t=1 time is defined as 0, and the definition can be replaced according to needs in a specific implementation scene.
Thus, the confidence characteristic of each moment in each section is obtained according to the difference value between the signal amplitude of each moment in each section in all IMF component signals except a certain IMF component signal and the signal amplitude of the previous moment in each section in all IMF component signals except a certain IMF component signal.
Finally, in this embodiment, the first signal difference value and the confidence coefficient feature at each moment in each segment are multiplied and accumulated to obtain the overall numerical proportion difference value existing in each segment in each IMF component signal, where the expression formula is as follows:
wherein mu mn Is present in the mth segment of the nth IMF component signalOverall numerical scale difference, a mnt Is the first signal difference value, k mnt Is the confidence feature at time t in the m segments in the nth IMF component signal. Mu (mu) mn The overall numerical proportion difference value existing in each segment in each IMF component is characterized, and the higher the overall numerical proportion difference value is, the more likely an equipment abnormal sound signal exists in a signal corresponding to a segment when EMD decomposition is carried out on the signal corresponding to the segment.
Thus, the overall numerical proportion size difference value existing in each segment in each IMF component signal is obtained according to the first signal difference value and the confidence coefficient characteristic of each moment in each segment.
Step S005: and obtaining the noise maintenance degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal.
Based on the amplitude fluctuation values of the signal amplitudes at all times in each segment obtained in step S003 and step S004 and the overall numerical proportion size difference value existing in each segment in each IMF component signal, there is the following analysis:
since the more the amplitude fluctuation value of the signal amplitude at all times in a certain segment is, the more the frequency included in the sound signal within the segment and the magnitude where the amplitude is located are, while the more extreme the amplitude distribution is, the more likely an abnormal sound signal of the device that we need is present.
Therefore, according to the amplitude fluctuation value of the signal amplitude at all times in each segment and the overall numerical proportion difference value existing in each segment of each IMF component signal, the formula for calculating the noise retention degree of all segments in each IMF component signal is as follows:
wherein C is n Is the noise retention level of all segments in the nth IMF component signal, M is the total number of segments in the nth IMF component signal,m is the total number of all segments in each signal, μ mn Is the overall numerical scale magnitude difference value present in the mth segment in the nth IMF component signal,is the arithmetic mean, epsilon, of the overall numerical scale magnitude differences present in all M segments in the nth IMF component signal m Is the amplitude fluctuation value of the signal amplitude at all times in the initial signal of the mth segment, norm (ε) m ) Amplitude fluctuation value epsilon representing signal amplitude at all times of mth segment in initial signal m The normalization operation is performed, the normalization allocation of the amplitude fluctuation value of the signal amplitude of each segment in the initial signal to the standard deviation of the original sound signal is represented, when the amplitude fluctuation value of the signal amplitude of each segment in the initial signal is larger, the standard deviation of the original sound signal is smaller, namely, the standard deviation of the original sound signal corresponding to a certain segment is taken as the confidence of the certain segment, and when the standard deviation is higher, the fluctuation degree of the signal existing in the segment is higher, so that the abnormal sound signal of equipment can exist in the segment besides the normal environment noise signal. The confidence of whether the segment is a noise signal feature is kept low in a certain IMF component signal. And carrying out standard deviation calculation on the numerical proportion difference accumulated value of each segment to obtain the fluctuation degree of the signal representing the degree of the noise signal maintained in the current component, wherein when the fluctuation degree of an IMF component signal is smaller, the IMF component signal is more stable, and the abnormal equipment sound signal of the IMF component signal is weaker.
Thus, the noise retention level of all the segments in each IMF component signal is obtained from the amplitude fluctuation values of the signal amplitudes at all the time points in each segment and the magnitude difference value of the overall numerical scale present in each segment in each IMF component signal.
Step S006: and normalizing according to the noise retention degree of all the segments in each IMF component signal to obtain a fluctuation degree weight, and obtaining the signal abnormality degree of each moment according to the COF abnormality outlier factor and the fluctuation degree weight which are calculated in each IMF component signal at each moment.
The greater the degree of fluctuation of the noise signal for all segments in each IMF component, the stronger the device anomaly sound signal characteristics that remain. The present embodiment is based on the noise retention degree C of all the segments in each IMF component signal obtained in step S005 n The normalized weight of the abnormal outlier factor obtained after the conventional COF outlier detection is carried out on the signal at each moment under each IMF component signal can be obtained, and the abnormal outlier factor obtained after the conventional COF outlier detection is carried out on the signal at each moment under all IMF component signals is multiplied and accumulated with the weight to obtain the signal abnormality degree at each moment, wherein the specific calculation formula is as follows:
abnormal outlier factor (gamma) obtained by conventional COF outlier detection of the signal at each time instant under the nth IMF component nt At the above fluctuation degree C n The finally acquired abnormal degree of the t moment is obtained after the weight of the abnormal outlier factors calculated in the n IMF component signals at the t moment is added up, namely:
wherein, gamma t Is the signal abnormality degree at the t-th time, N is the number of IMF component signals, gamma nt Is an abnormal outlier factor obtained by performing conventional COF outlier detection on a signal at a t time under an nth IMF component signal (the calculation of the COF outlier factor is a conventional technique, and is not described in detail in this embodiment), norm (C) n ) Representing the degree of noise retention C for all segments in each IMF component signal n And (3) performing linear normalization operation to characterize the normalization weight of the outlier factor. The smaller the noise retention degree in a certain IMF component signal, the smaller the confidence degree when the equipment abnormal sound recognition is performed in the IMF component signal, and after COF outlier factor calculation is performed on the signal under each IMF component signal, the signal abnormality degree at each moment after weighted summation is obtained.
So far, the fluctuation degree weight is obtained through normalization according to the noise retention degree of all the segments in each IMF component signal, and the signal abnormality degree of each moment is obtained through weighted summation of the abnormality outlier factor obtained through conventional COF outlier detection according to the signal of each moment under each IMF component signal and the fluctuation degree weight.
Step S007: and judging an abnormal signal according to the abnormal degree of each moment and obtaining corresponding abnormal equipment.
According to the step process of repeating steps S002 to S006, the signal abnormality degree at each time of the sound signal of the whole day on the site is obtained. And carrying out linear normalization according to the signal abnormality degree of the sound signal of the whole day on the site at each moment to obtain an abnormality detection value. Comparing the value of the abnormal detection value with a preset abnormal threshold value, and judging according to a comparison result: and when the abnormality detection value exceeds the abnormality threshold, the signal is an abnormality signal, and otherwise, the signal is a normal signal. In this embodiment, the preset abnormal threshold value is equal to 0.8, and other values may be set during implementation, which is not specifically limited.
After the abnormal signals are acquired and intercepted, the specific equipment generating abnormal sound can be found out by analyzing and processing the sound signals in the prior art. This technique is known as acoustic monitoring or audio recognition. The technology is based on machine learning and data analysis technology, utilizes advanced signal processing algorithms and pattern recognition technology to analyze the sound generated by a specific device and creates a feature vector representing the sound features of the device. These feature vectors are then used to train a classifier or neural network model to automatically identify normal and abnormal sounds of the device. When the equipment is abnormal, the system can detect the abnormal sounds and find out the corresponding abnormal equipment, and the abnormal equipment is sent to the cloud for reporting, so that maintenance personnel are notified to overhaul in time, and normal development of the building engineering is ensured.
So far, the embodiment obtains the corresponding abnormal equipment and realizes the intelligent acceptance management method for the quality of the building engineering based on cloud edge cooperation.
The invention provides an embodiment, which provides a cloud-edge cooperation-based intelligent acceptance management system for building engineering quality, comprising the following modules:
and a data acquisition module: and collecting the sound signals of the whole day on the site.
And a data processing module: preprocessing the sound signal to obtain an initial signal, and performing EMD (empirical mode decomposition) according to the initial signal to obtain a plurality of IMF (inertial measurement unit) component signals; segmenting according to the initial signal and the moments of all IMF component signals to obtain each segment of each signal; obtaining amplitude fluctuation values of signal amplitudes at all moments in each segment according to each segment of the initial signal; acquiring signal difference of an initial signal and a component signal at each moment in each segment, marking the signal difference as a first signal difference value, obtaining a confidence coefficient characteristic at each moment in each segment according to the signal difference of the component signal at the adjacent moment in each segment, and obtaining an integral numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic at each moment; obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal; and obtaining fluctuation degree weights according to the noise retention degrees of all the segments in each IMF component signal, and obtaining the signal abnormality degree of each moment according to the COF abnormality outlier factors and the fluctuation degree weights obtained by calculation in each IMF component signal at each moment.
The abnormality judgment module: and judging an abnormal signal according to the abnormal degree of each moment and obtaining corresponding abnormal equipment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The intelligent acceptance management method for the quality of the building engineering based on cloud edge cooperation is characterized by comprising the following steps of:
collecting a sound signal of the whole day on a construction site, preprocessing the sound signal to obtain an initial signal, and carrying out EMD (empirical mode decomposition) according to the initial signal to obtain a plurality of IMF (intrinsic mode function) component signals;
segmenting according to the initial signal and the moments of all IMF component signals to obtain each segment of each signal;
obtaining amplitude fluctuation values of signal amplitudes at all moments in each segment according to each segment of the initial signal;
acquiring signal difference of an initial signal and an IMF component signal at each moment in each segment, marking the signal difference as a first signal difference value, obtaining a confidence coefficient characteristic of each moment in each segment according to the signal difference of the IMF component signal at the adjacent moment in each segment, and obtaining an integral numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic of each moment in each segment;
obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal;
obtaining fluctuation degree weights according to the noise retention degrees of all the segments in each IMF component signal, and obtaining signal abnormality degrees at each moment according to COF abnormality outlier factors and the fluctuation degree weights obtained by calculation in each IMF component signal at each moment;
judging an abnormal signal according to the abnormal degree of each moment and obtaining corresponding abnormal equipment;
the method comprises the specific steps of obtaining the signal difference of an initial signal and an IMF component signal at each moment in each segment, recording the signal difference as a first signal difference value, and obtaining the confidence coefficient characteristic of each moment in each segment according to the signal difference of the IMF component signal at the adjacent moment in each segment, wherein the specific steps are as follows:
acquiring a signal amplitude of each moment in each segment in each IMF component signal, normalizing the signal amplitude of each moment in each segment in an initial signal to obtain a first amplitude, normalizing the signal amplitude of the same moment in the same segment in each IMF component signal to obtain a second amplitude, taking a difference between the first amplitude and the second amplitude and taking an absolute value to obtain a signal difference of each moment in each segment, and marking the signal difference of each moment in each segment as a first signal difference value; meanwhile, acquiring signal amplitude of each moment in each IMF component signal except a certain IMF component signal, marking the signal amplitude as a third amplitude, acquiring signal amplitude of the previous moment in each moment except the certain IMF component signal as a fourth amplitude, taking difference according to the third amplitude and the fourth amplitude, taking absolute value summation, dividing the absolute value by the quantity of IMF component signals obtained by EMD decomposition of the initial signal, and obtaining confidence coefficient characteristics of each moment;
the calculation formula for obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal is as follows:
wherein C is n Is the noise retention level of all segments in the nth IMF component signal, M is the total number of all segments in each signal, μ mn Is the overall numerical scale magnitude difference value present in the mth segment in the nth IMF component signal,is the arithmetic mean, epsilon, of the overall numerical scale magnitude differences present in all M segments in the nth IMF component signal m Is the amplitude fluctuation value of the signal amplitude at all times in the initial signal of the mth segment, norm (ε) m ) Amplitude fluctuation value epsilon representing signal amplitude at all times of mth segment in initial signal m Performing linear normalization operation;
the fluctuation degree weight is obtained according to the noise retention degree of all the segments in each IMF component signal, and the method comprises the following specific steps:
normalization is performed according to the noise retention levels of all the segments in each IMF component signal to obtain the fluctuation degree weight.
2. The intelligent acceptance management method for building engineering quality based on cloud edge cooperation according to claim 1, wherein the steps of segmenting each segment of each signal according to the initial signal and the moments of all IMF component signals comprise the following specific steps:
and segmenting the signals according to time according to the obtained initial signals and all IMF component signals, and dividing all signals comprising the initial signals and all IMF component signals into a plurality of segments according to a fixed segment size to obtain each segment of each signal.
3. The intelligent acceptance management method for the quality of the building engineering based on cloud edge cooperation according to claim 1, wherein the method for obtaining the amplitude fluctuation value of the signal amplitude at all moments in each segment according to each segment of the initial signal comprises the following specific steps:
the method comprises the steps of obtaining the amplitude of each moment in each segment in an initial signal, and obtaining the calculation formula of the amplitude fluctuation value of the signal amplitude at all moments in each segment according to the segments, the moment and the signal amplitude, wherein the calculation formula is as follows:
wherein ε m Is the amplitude fluctuation value of the signal amplitude at all moments in the mth segment of the initial signal, M is the total number of all segments in each signal, M is the label of a segment in all segments of the initial signal and has M E [1, M]T is the number of instants contained in each segment of the initial signal, T is the label of a certain instant contained in each segment of the initial signal and has T e 1,T]，a mt is the signal amplitude at time t in the mth segment of the initial signal,is the arithmetic mean of the signal amplitudes at all times in the mth segment in the initial signal, exp () is an exponential function with a base of natural constant.
4. The intelligent acceptance management method for building engineering quality based on cloud edge cooperation according to claim 1, wherein the step of obtaining the overall numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic of each moment in each segment comprises the following specific steps:
and multiplying and accumulating according to the first signal difference value and the confidence coefficient characteristic of each moment in each segment to obtain the integral numerical proportion difference value existing in each segment in each IMF component signal.
5. The intelligent acceptance management method for building engineering quality based on cloud edge cooperation according to claim 1, wherein the method for obtaining the signal anomaly degree of each moment according to the COF anomaly outlier factor and the fluctuation degree weight calculated in each IMF component signal at each moment comprises the following specific steps:
and performing conventional COF outlier detection according to the signal at each moment under each IMF component to obtain a COF outlier factor of each moment in each IMF component signal, and multiplying and accumulating the COF outlier factor and the fluctuation degree weight of each moment in each IMF component signal to obtain the signal abnormality degree at each moment.
6. Intelligent acceptance management system for building engineering quality based on cloud edge cooperation is characterized by comprising the following modules:
and a data acquisition module: the method is used for collecting sound signals of the whole day on the site;
and a data processing module: the method comprises the steps of preprocessing a sound signal to obtain an initial signal, and carrying out EMD (empirical mode decomposition) according to the initial signal to obtain a plurality of IMF (intrinsic mode function) component signals; segmenting according to the initial signal and the moments of all IMF component signals to obtain each segment of each signal; obtaining amplitude fluctuation values of signal amplitudes at all moments in each segment according to each segment of the initial signal; acquiring signal difference of an initial signal and an IMF component signal at each moment in each segment, marking the signal difference as a first signal difference value, obtaining a confidence coefficient characteristic of each moment in each segment according to the signal difference of the IMF component signal at the adjacent moment in each segment, and obtaining an integral numerical proportion difference value existing in each segment in each IMF component signal according to the first signal difference value and the confidence coefficient characteristic of each moment; obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal; obtaining fluctuation degree weights according to the noise retention degrees of all the segments in each IMF component signal, and obtaining signal abnormality degrees at each moment according to COF abnormality outlier factors and the fluctuation degree weights obtained by calculation in each IMF component signal at each moment;
the abnormality judgment module: judging an abnormal signal according to the abnormal degree of each moment and obtaining corresponding abnormal equipment;
the method comprises the specific steps of obtaining the signal difference of an initial signal and an IMF component signal at each moment in each segment, recording the signal difference as a first signal difference value, and obtaining the confidence coefficient characteristic of each moment in each segment according to the signal difference of the IMF component signal at the adjacent moment in each segment, wherein the specific steps are as follows:
acquiring a signal amplitude of each moment in each segment in each IMF component signal, normalizing the signal amplitude of each moment in each segment in an initial signal to obtain a first amplitude, normalizing the signal amplitude of the same moment in the same segment in each IMF component signal to obtain a second amplitude, taking a difference between the first amplitude and the second amplitude and taking an absolute value to obtain a signal difference of each moment in each segment, and marking the signal difference of each moment in each segment as a first signal difference value; meanwhile, acquiring signal amplitude of each moment in each IMF component signal except a certain IMF component signal, marking the signal amplitude as a third amplitude, acquiring signal amplitude of the previous moment in each moment except the certain IMF component signal as a fourth amplitude, taking difference according to the third amplitude and the fourth amplitude, taking absolute value summation, dividing the absolute value by the quantity of IMF component signals obtained by EMD decomposition of the initial signal, and obtaining confidence coefficient characteristics of each moment;
the calculation formula for obtaining the noise retention degree of all the segments in each IMF component signal according to the amplitude fluctuation value of the signal amplitude at all the moments in each segment and the integral numerical proportion difference value existing in each segment in each IMF component signal is as follows:
wherein C is n Is the noise retention level of all segments in the nth IMF component signal, M is the total number of all segments in each signal, μ mn Is the overall numerical scale magnitude difference value present in the mth segment in the nth IMF component signal,is the arithmetic mean, epsilon, of the overall numerical scale magnitude differences present in all M segments in the nth IMF component signal m Is the amplitude fluctuation value of the signal amplitude at all times in the initial signal of the mth segment, norm (ε) m ) Amplitude fluctuation value epsilon representing signal amplitude at all times of mth segment in initial signal m Performing linear normalization operation;
the fluctuation degree weight is obtained according to the noise retention degree of all the segments in each IMF component signal, and the method comprises the following specific steps:
normalization is performed according to the noise retention levels of all the segments in each IMF component signal to obtain the fluctuation degree weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310577867.2A CN116609440B (en) | 2023-05-22 | 2023-05-22 | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310577867.2A CN116609440B (en) | 2023-05-22 | 2023-05-22 | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116609440A CN116609440A (en) | 2023-08-18 |
| CN116609440B true CN116609440B (en) | 2023-11-28 |
Family
ID=87681317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310577867.2A Active CN116609440B (en) | 2023-05-22 | 2023-05-22 | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116609440B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117375626B (en) * | 2023-12-08 | 2024-03-08 | 北京奥力斯特投资管理有限公司 | Intelligent heat supply abnormal data transmission method and system |
| CN117889945B (en) * | 2024-03-14 | 2024-05-31 | 河南鹏飞建设工程有限公司 | Highway bridge construction vibration testing method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109560984A (en) * | 2018-11-13 | 2019-04-02 | 苏宁易购集团股份有限公司 | A kind of network service response time method for detecting abnormality and device |
| WO2019179340A1 (en) * | 2018-03-19 | 2019-09-26 | 河北工业大学 | Eemd- and msb-based failure feature extraction method for rolling-element bearing |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN115325936A (en) * | 2022-10-10 | 2022-11-11 | 南通欧惠纺织科技有限公司 | Method for detecting abnormity of heald frame of textile machine |
| CN116013087A (en) * | 2023-03-27 | 2023-04-25 | 东莞市城建规划设计院 | Traffic flow statistical method based on urban moving vehicle detection |
-
2023
- 2023-05-22 CN CN202310577867.2A patent/CN116609440B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019179340A1 (en) * | 2018-03-19 | 2019-09-26 | 河北工业大学 | Eemd- and msb-based failure feature extraction method for rolling-element bearing |
| CN109560984A (en) * | 2018-11-13 | 2019-04-02 | 苏宁易购集团股份有限公司 | A kind of network service response time method for detecting abnormality and device |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN115325936A (en) * | 2022-10-10 | 2022-11-11 | 南通欧惠纺织科技有限公司 | Method for detecting abnormity of heald frame of textile machine |
| CN116013087A (en) * | 2023-03-27 | 2023-04-25 | 东莞市城建规划设计院 | Traffic flow statistical method based on urban moving vehicle detection |
Non-Patent Citations (1)
| Title |
|---|
| Shuai Yang等.《A New Method of Bearing Remaining Useful Life Based on Life Evolution and SE-ConvLSTM Neural Network》.《Machines》.2022,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116609440A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116609440B (en) | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation | |
| Koizumi et al. | Unsupervised detection of anomalous sound based on deep learning and the neyman–pearson lemma | |
| EP3680639B1 (en) | Abnormality model learning device, method, and program | |
| US20190376840A1 (en) | Anomalous sound detection apparatus, degree-of-anomaly calculation apparatus, anomalous sound generation apparatus, anomalous sound detection training apparatus, anomalous signal detection apparatus, anomalous signal detection training apparatus, and methods and programs therefor | |
| US20200271756A1 (en) | System and method for identification of an airborne object | |
| WO1997008627A1 (en) | A neural network based system for equipment surveillance | |
| CN112414694B (en) | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology | |
| CN116380445B (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN111291481B (en) | Bayesian model-based structure early warning analysis method | |
| Liu et al. | A deep support vector data description method for anomaly detection in helicopters | |
| CN113707175B (en) | Acoustic event detection system based on feature decomposition classifier and adaptive post-processing | |
| CN111260024A (en) | Fault detection method and system based on combination of long-term and short-term memory and typical correlation | |
| Zhang et al. | Complementary ensemble adaptive local iterative filtering and its application to rolling bearing fault diagnosis | |
| CN116364108A (en) | Transformer voiceprint detection method and device, electronic equipment and storage medium | |
| Zhang et al. | Automatic recognition of porcine abnormalities based on a sound detection and recognition system | |
| CN112329535B (en) | CNN-based quick identification method for low-frequency oscillation modal characteristics of power system | |
| CN115343573A (en) | Voiceprint model evolution equipment fault fusion judgment method facing power grid monitoring | |
| Zhang et al. | Detection capability for incipient faults in a noisy environment using PDF and CDF based techniques: a comparative study | |
| CN112232329A (en) | Multi-core SVM training and alarming method, device and system for intrusion signal recognition | |
| CN116448062B (en) | Bridge settlement deformation detection method, device, computer and storage medium | |
| CN117473275B (en) | Energy consumption detection method for data center | |
| Yang et al. | Empirical probability density cumulative sum for incipient fault detection | |
| CN117079416B (en) | Multi-person 5D radar falling detection method and system based on artificial intelligence algorithm | |
| CN117262942A (en) | Elevator abnormality detection method, elevator abnormality detection device, computer equipment and storage medium |
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 |