CN116108008A - Decorative material formaldehyde detection data processing method - Google Patents
Decorative material formaldehyde detection data processing method Download PDFInfo
- Publication number
- CN116108008A CN116108008A CN202310388990.XA CN202310388990A CN116108008A CN 116108008 A CN116108008 A CN 116108008A CN 202310388990 A CN202310388990 A CN 202310388990A CN 116108008 A CN116108008 A CN 116108008A
- Authority
- CN
- China
- Prior art keywords
- sub
- segment
- sequence
- data
- value
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method for processing decorative material formaldehyde detection data, which comprises the following steps: acquiring a first time sequence and a second time sequence at different positions, and further acquiring a first sub-segment sequence and a second sub-segment sequence under each segment; obtaining an abnormality index coefficient according to the difference between the second sub-segment sequences and the abnormality condition of the data; obtaining a comprehensive abnormality index according to the abnormality index coefficient, the first sub-segment sequence and the data in the second sub-segment sequence; obtaining abnormal weight of each data in the second time sequence according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data, carrying out filtering processing on the data according to the abnormal weight, and obtaining corrected formaldehyde detection data according to the environment detection data obtained by the filtering processing and the data in the first time sequence. The invention solves the problem that the result of correcting the formaldehyde detection data is inaccurate, and can obtain more accurate corrected formaldehyde detection data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for processing formaldehyde detection data of a decorative material.
Background
The interior material and furniture contain a large amount of aldehydes, which affect the health of people, so the detection of formaldehyde concentration is particularly important. The traditional formaldehyde detection method comprises a spectroscopical method, a polarography method and the like, but the detection instruments are large in size and high in price, and are not suitable for common users. Therefore, the novel formaldehyde sensor has the advantages of small volume, low cost and convenient operation. However, the detected formaldehyde data is also interfered by environmental factors, so that larger errors occur in the formaldehyde detection data, and the collected formaldehyde detection data is corrected by the environmental detection data in the prior art. However, when detecting the environmental data, an abnormal value of the environmental data may occur, so that the correction result is less accurate, and therefore, it is important to clean the environmental detection data through filtering.
The conventional average filtering denoising method is often used for filtering the data, but the method is used for performing indiscriminate smoothing on the data, so that normal data information can be lost to a certain extent while denoising, the filtered data is inaccurate, and the result of correcting formaldehyde detection data by using the filtered environment detection data is inaccurate.
Disclosure of Invention
In order to solve the technical problem that the result of correcting formaldehyde detection data by using filtered environment detection data is inaccurate, the invention aims to provide a decorative material formaldehyde detection data processing method, which adopts the following technical scheme:
acquiring a first time sequence corresponding to formaldehyde detection data at different positions and a second time sequence corresponding to environment detection data, and segmenting the first time sequence and the second time sequence to obtain a first sub-segment sequence and a second sub-segment sequence under each segment;
obtaining an abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-segment sequence corresponding to any position under each segment and the second sub-segment sequences corresponding to other positions and the abnormal condition of the data in the second sub-segment sequence;
obtaining a comprehensive abnormality index at each position of each segment according to the abnormality index coefficient, the corresponding first sub-segment sequence and the corresponding second sub-segment sequence at each position of each segment;
obtaining abnormal weights of each data in the second time sequence at each position according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data in the corresponding second sub-segment sequence, carrying out filtering processing on the data in the second time sequence at each position according to the abnormal weights, and obtaining corrected formaldehyde detection data according to the environment detection data obtained by the filtering processing and the data in the first time sequence.
Preferably, the obtaining the abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-segment sequence corresponding to any position under each segment and the second sub-segment sequences corresponding to other positions and the abnormality condition of the data in the second sub-segment sequence specifically includes:
STL decomposition is carried out on the second time sequence, a periodic sequence corresponding to a second sub-segment sequence obtained through decomposition is recorded as a second sub-periodic sequence, and a residual sequence corresponding to the second sub-segment sequence obtained through decomposition is recorded as a second sub-residual sequence;
and obtaining an abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-period sequence corresponding to the second sub-segment sequence at any position under each segment and the second sub-period sequences corresponding to the second sub-segment sequences at other positions and the residual value in the second sub-residual sequence corresponding to the second sub-segment sequence.
Preferably, the obtaining the abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-period sequence corresponding to the second sub-segment sequence at any position under each segment and the second sub-period sequences corresponding to the second sub-segment sequences at other positions and the residual data in the second sub-residual sequence corresponding to the second sub-segment sequence specifically includes:
Marking any one position as a target position, for a second sub-segment sequence at the target position under any one segment,
recording any one characteristic value in a second sub-period sequence corresponding to the second sub-period sequence as a target characteristic value, and calculating the average value of the absolute value of the difference value between the target characteristic value and each characteristic value in the second sub-period sequence corresponding to the second sub-period sequence at other positions to obtain the characteristic difference degree of the target characteristic value; the characteristic value is a normalized value of a crest value or a trough value;
in a second sub-period sequence corresponding to the second sub-segment sequence, taking a data point with a data value being a first preset value as a partition point, dividing the second sub-period sequence into at least two sub-segments by utilizing the partition point, and acquiring a characteristic value corresponding to each sub-segment and a residual value corresponding to each sub-segment in a second sub-residual sequence;
calculating the sum of all residual values under the sub-segments corresponding to the target characteristic value to obtain an abnormality index of the target characteristic value;
taking the product of the characteristic difference degree and the abnormality degree index of the target characteristic value as an abnormality index of the target characteristic value; taking the normalized value of the sum of the abnormality indexes of all the characteristic values as the abnormality index coefficient of the corresponding second sub-segment sequence at the target position under the segment.
Preferably, the obtaining the comprehensive abnormality index at each position under each segment according to the abnormality index coefficient and the variation condition of the data in the first sub-segment sequence and the second sub-segment sequence corresponding to each position under each segment specifically includes:
calculating the absolute value of the difference between the first data and the last data in the first sub-segment sequence at any position of any segment to obtain the change amplitude of the first sub-segment sequence;
for a second sub-segment sequence corresponding to any one of the environment detection data, calculating the absolute value of the difference between the first data and the last data in the second sub-segment sequence to obtain the change amplitude of the second sub-segment sequence; calculating the product of the abnormality index coefficient, the change amplitude and the preset influence degree super-parameter of the second sub-segment sequence at the position under the segmentation to obtain the influence degree coefficient of the environment detection data;
and calculating the sum value of influence coefficients of all environment detection data, and taking the normalized value of the variation amplitude of the first sub-segment sequence and the absolute value of the difference value of the sum value as the comprehensive abnormal index at the position under the segment.
Preferably, the obtaining the abnormal weight of each data in the second time sequence at each position according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data in the corresponding second sub-segment sequence specifically includes:
For a second sub-segment sequence at any position under any one segment, calculating the product of an abnormality index coefficient and a comprehensive abnormality index of the second sub-segment sequence;
recording any one data in the second sub-segment sequence as selected data, calculating the absolute value of the difference between the selected data and the last data adjacent to the selected data, calculating the absolute value of the difference between the selected data and the next data adjacent to the selected data, and taking the normalized value of the product between the sum of the absolute values of the two differences and the product as the abnormal weight of the selected data; obtaining abnormal weight of each data in the second time sequence at each position; the selected data cannot be an endpoint in the second timing sequence.
Preferably, the segmenting the first time sequence and the second time sequence to obtain the first sub-segment sequence and the second sub-segment sequence under each segment specifically includes:
for any one first time sequence, taking each peak value and each valley value of data in the first time sequence as a segmentation point, segmenting the first time sequence, and obtaining a first sub-segment sequence under each segmentation;
and for any one second time sequence, acquiring data points in the second time sequence at the same time as the segmentation point, and segmenting the second time sequence by the data points to obtain a second sub-segment sequence under each segmentation.
Preferably, the filtering processing of the data in the second time sequence at each position according to the abnormal weight specifically includes:
and filtering the data in the second time sequence by using a preset filtering window, wherein the filtering weight of the central data in the filtering window is the difference value between the numerical value 1 and the abnormal weight corresponding to the data, and the filtering weights of other data in the filtering window are the abnormal weights corresponding to the data.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, the time sequence corresponding to the formaldehyde detection data and the environment detection data at different positions is firstly obtained, the obtained time sequence is subjected to sectional processing to obtain the first sub-segment sequence and the second sub-segment sequence under each section, and the variation characteristics of the formaldehyde detection data and the environment detection data under each section can be respectively analyzed by respectively analyzing the sub-segment sequences obtained by the sections, so that the analysis result is more accurate. Then, analyzing self abnormal conditions of the environment detection data at each position under each segment, obtaining an abnormal index coefficient of a second sub-segment sequence corresponding to each position under each segment according to differences between the second sub-segment sequences at any position under each segment and other positions and the abnormal conditions of the data in the second sub-segment sequences, taking the differences of the environment detection data between different positions into consideration, and simultaneously taking the abnormal conditions of the self data in the second sub-segment sequences into consideration, and reflecting the possibility degree of the abnormal data in the second sub-segment sequences by using the abnormal index coefficient; further, according to the abnormality index coefficient, combining the change difference condition between formaldehyde detection data and environment detection data, comprehensively obtaining comprehensive abnormality indexes at each position under each segment, and integrally reflecting the possibility degree of abnormal data in the data at the corresponding position under the corresponding segment by utilizing the comprehensive abnormality indexes; finally, according to the abnormal index coefficient and the comprehensive abnormal index, and by combining the difference condition of the data in the corresponding second sub-segment sequence, the abnormal weight of each data in the second time sequence is obtained, the abnormal weight represents the possibility that the data in the second sub-segment sequence is abnormal data, and then the data in the second time sequence at each position is subjected to filtering processing according to the abnormal weight, so that a more accurate filtering result is obtained, the normal data has more reserved data characteristics when being filtered, the loss of data information is reduced, and the corrected formaldehyde detection data is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for processing formaldehyde detection data of a decorative material according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to specific implementation, structure, characteristics and effects of a method for processing formaldehyde detection data of a decorative material according to the present invention, with reference to the accompanying drawings and preferred embodiments. 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 following specifically describes a specific scheme of the method for processing formaldehyde detection data of a decorative material provided by the invention with reference to the accompanying drawings.
Examples:
referring to fig. 1, a method flowchart of a method for processing formaldehyde detection data of a decorative material according to an embodiment of the invention is shown, the method includes the following steps:
step one, a first time sequence corresponding to formaldehyde detection data at different positions and a second time sequence corresponding to environment detection data are obtained, and the first time sequence and the second time sequence are segmented to obtain a first sub-segment sequence and a second sub-segment sequence under each segment.
Firstly, because the detected formaldehyde data is also interfered by environmental factors to cause larger errors between the formaldehyde detection data and the actual occurrence, the formaldehyde detection data is acquired, and meanwhile, related detection data in the current environment, such as environmental interference factors of temperature, humidity, ethanol, ammonia gas concentration and the like, are also required to be acquired. Meanwhile, considering that the formaldehyde gas concentration may be different at different locations in the room, data collection is required at a plurality of locations in the room.
Specifically, formaldehyde gas concentrations are collected at a plurality of different positions in a room to serve as formaldehyde detection data, and the formaldehyde detection data collected at one position at different moments in a set time period form a time sequence, and the time sequence is recorded as a first time sequence. For example, temperature, humidity, ethanol and ammonia gas concentrations are collected at a plurality of different positions in a room as environment detection data, a class of the environment detection data can be selected according to a specific implementation scene, and the environment detection data collected at one position at different moments in a set time period form a time sequence, which is recorded as a second time sequence.
It should be noted that, the plurality of different indoor positions may be four corners in a room, and an implementer may set the four corners according to a specific implementation scenario, and collect formaldehyde detection data and environment detection data at the same position, that is, one position corresponds to one first time sequence and a plurality of second time sequences. Meanwhile, the lengths of the first time sequence and the second time sequence are the same, namely the time length and the time quantity corresponding to the first time sequence and the second time sequence and the quantity of contained data are the same. In the present embodiment, the time length of the set time period is set to 1 day, the time interval between adjacent two times is set to 1 hour, and the practitioner can set according to the specific implementation scenario.
Then, because the same decoration material is influenced by external parameters such as space size and ventilation condition at different positions in the room, a certain difference condition exists in detection data at different positions in the room, and meanwhile, the collected data is abnormal possibly due to the abnormal condition of the sensor, so that the noise removal processing of the data by the conventional mean value filtering algorithm cannot achieve a good effect for the complex data condition. In order to accurately analyze the change condition of the data, in this embodiment, the collected data in the time sequence is divided into a plurality of data segments for analysis.
Specifically, the first time sequence and the second time sequence are segmented respectively to obtain a first sub-segment sequence and a second sub-segment sequence under each segment.
In this embodiment, for any one first time sequence, each peak value and each valley value of data in the first time sequence are used as segmentation points, and the first time sequence is segmented to obtain a first sub-segment sequence under each segment; and for any one second time sequence, acquiring data points in the second time sequence at the same time as the segmentation point, and segmenting the second time sequence by the data points to obtain a second sub-segment sequence under each segmentation.
As the peak value and the valley value are extreme values in the first time sequence, the data between two adjacent extreme values are used as a segment, and the data change condition under each segment can be better analyzed. For example, assuming that 24 data are shared in the first sequence, the data corresponding to the 6 th time is a peak value and the data corresponding to the 16 th time is a valley value, the first sequence is divided into a first sub-segment sequence of three segments by using the data corresponding to the 6 th time and the data corresponding to the 16 th time as segment points. Meanwhile, in the plurality of second time sequence sequences, the data corresponding to the 6 th moment and the data corresponding to the 16 th moment are taken as segmentation points respectively, and the second time sequence is divided into second sub-segment sequences under three segments. In this embodiment, the same segment point exists under both adjacent segments. In other embodiments, a segmentation point may also exist under only one segment. Based on this, a first sub-segment sequence and a second sub-segment sequence of a plurality of different environmental monitoring data are corresponding at each location under each segment.
In order to better analyze the data change condition of formaldehyde detection data and environment detection data, the STL algorithm is utilized to decompose the first time sequence and the second time sequence respectively, so that a trend sequence, a periodic sequence and a residual sequence corresponding to the first time sequence can be obtained, and a trend sequence, a periodic sequence and a residual sequence corresponding to the second time sequence can be obtained. The trend sequence, the periodic sequence and the residual sequence corresponding to the first time sequence are segmented respectively, the trend sequence, the periodic sequence and the residual sequence corresponding to the second time sequence are segmented, the segmentation method is the same as that of the first time sequence and the second time sequence respectively, the periodic sequence corresponding to the first sub-segment sequence obtained through decomposition is marked as a first sub-periodic sequence, and the residual sequence corresponding to the first sub-segment sequence obtained through decomposition is marked as a second sub-residual sequence. And marking the periodic sequence corresponding to the second sub-segment sequence obtained by decomposition as a second sub-periodic sequence, and marking the residual sequence corresponding to the second sub-segment sequence obtained by decomposition as a second sub-residual sequence.
It should be noted that, the trend sequence, the period sequence and the sequence length between the residual sequences corresponding to the first time sequence are the same, so that the plurality of first sub-segment sequences corresponding to the first time sequence also have corresponding first sub-trend sequences, first sub-period sequences and first sub-residual sequences. Similarly, the second time sequence has a corresponding second sub-trend sequence, second sub-period sequence and second sub-residual sequence. The trend sequence can reflect the trend change of the corresponding time sequence, the periodic sequence can reflect the periodic change of the corresponding time sequence, the residual sequence can reflect the abnormal condition of the corresponding time sequence, and the STL algorithm is utilized to decompose the time sequence into known techniques, which are not described too much.
Based on this, in other embodiments, the specific method of segmenting the first time sequence and the second time sequence to obtain the first sub-segment sequence and the second sub-segment sequence under each segment may further be to obtain a peak and a trough in the trend sequence corresponding to the first time sequence, and segment the first time sequence by using each peak and trough as a segmentation point and using the segmentation point to obtain the first sub-segment sequence under each segment; and acquiring data points in the second time sequence at the same time as the segmentation points, and segmenting the second time sequence by the data points to obtain a second sub-segment sequence under each segment.
In this embodiment, the segmentation operation is performed based on the trend of the formaldehyde detection data, and the segments corresponding to the environment detection data have the same time period, but the trend of the change may have a certain difference, that is, the segmentation points in the second time sequence are not necessarily peaks or valleys, so that the analysis of the environment detection data under each segment is required.
Step two, obtaining the abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-segment sequence corresponding to any position under each segment and the second sub-segment sequences corresponding to other positions and the abnormality condition of the data in the second sub-segment sequences.
Firstly, analysis of abnormal conditions is carried out on collected environment detection data, and for the same environment detection data, under normal conditions, the changes of the collected data at different positions are similar or identical, so that the changes of the data at different positions in time sequence are similar or identical, and based on the analysis, the change difference of the data can be reflected more intuitively after the peak value and the valley value in the second sub-segment sequence are normalized.
Further, according to the difference between the second sub-period sequence corresponding to the second sub-segment sequence at any position under each segment and the second sub-period sequences corresponding to the second sub-segment sequences at other positions and residual data in the second sub-residual sequences corresponding to the second sub-segment sequences, the abnormal index coefficient of the second sub-segment sequence corresponding to each position under each segment is obtained.
Specifically, in the present embodiment, description will be given taking, as an example, one kind of environment detection data corresponding to any one position, for example, temperature data at any one position. Meanwhile, a second time sequence corresponds to the position, and a second sub-segment sequence under a plurality of segments is described as an example of the second sub-segment sequence under any one segment in the present embodiment.
Marking any one position as a target position, marking any one characteristic value in a second sub-period sequence corresponding to the second sub-period sequence as a target characteristic value for a second sub-period sequence at the target position of any one subsection, and calculating the average value of the absolute value of the difference value between the target characteristic value and each characteristic value in the second sub-period sequence corresponding to the second sub-period sequence at other positions to obtain the characteristic difference degree of the target characteristic value; the characteristic value is a normalized value of a peak value or a trough value.
It should be noted that, for a feature difference corresponding to a feature value, for any one feature value in the second sub-segment sequence at the target position under any one segment, the absolute value of the difference between the feature value and each feature value in the second sub-segment sequence at other positions is calculated, and the average value of the absolute values of the differences corresponding to all feature values in all second sub-segment sequences at other positions of the feature value is calculated, so as to obtain the feature difference.
In a second sub-period sequence corresponding to the second sub-segment sequence, taking a data point with a data value as a first preset value as a division point, dividing the second sub-period sequence into at least two sub-segments by using the division point, and obtaining a characteristic value corresponding to each sub-segment and a residual value corresponding to each sub-segment in a second sub-residual sequence.
It should be noted that, in the periodic sequence obtained by decomposing the time sequence by using the STL algorithm, the data all generate periodic fluctuations on the abscissa axis, so the periodic sequence may be divided into a plurality of data segments by using the abscissa axis, and each data segment may include one or more extremum values. Based on this, in this embodiment, the value of the first preset value is 0, and the practitioner can set according to the specific implementation scenario. In this embodiment, the same segmentation point exists in both adjacent sub-segments. In other embodiments, a partition point may also exist in only one sub-segment.
Further, in each sub-segment in the second sequence of sub-segments there may be one or more peak or trough values, i.e. there may be a plurality of eigenvalues. Since the sequences in this embodiment are all time sequences, when the second sub-segment sequence is segmented, the second sub-residual sequence also has a corresponding sub-segment, so that a residual value corresponding to each sub-segment in the second sub-residual sequence can be obtained.
Calculating the sum of all residual values under the sub-segments corresponding to the target characteristic value to obtain an abnormality index of the target characteristic value; taking the product of the characteristic difference degree and the abnormality degree index of the target characteristic value as an abnormality index of the target characteristic value; taking a normalized value of the sum of the abnormality indexes of all the characteristic values as an abnormality index coefficient of a corresponding second sub-segment sequence at the target position under the segment, and expressing the abnormality index coefficient as follows by a formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
an abnormality index coefficient representing a second sub-segment sequence corresponding to the nth segment of the a-th environment detection data at the ith position, i.e., an abnormality index coefficient representing a second sub-segment sequence corresponding to the nth segment at the target position;
representing the feature difference degree of the mth feature value in the corresponding second sub-segment sequence under the nth segment at the ith position, wherein the mth feature value is the target feature value, namely
A feature difference degree representing a target feature value;
representing the number of eigenvalues contained in the corresponding second sub-segment sequence under the nth segment at the ith position;
representing the c-th residual value under the sub-segment corresponding to the m-th characteristic value in the second sub-segment sequence corresponding to the n-th segment at the i-th position,
representing the number of all residual values contained in the sub-segment corresponding to the m characteristic value in the second sub-segment sequence corresponding to the n segment at the i position; norm () represents a normalization function, which in this embodiment represents the L1 norm or L2 norm of the computed normalization array.
For the same environment detection data, the periodic characteristics refer to that the environment detection data at different positions have the same periodic variation trend when not influenced by noise data, and the characteristic value variation rule on the corresponding time sequence reflects the normal variation trend of the environment detection data, so that the characteristic difference degree
The larger the value of the index is, the larger the difference between the characteristic value at a certain position and the characteristic values at other positions is, and further the larger the difference between the change trend of the environment detection data at the position and the change trend of the environment detection data at other positions is, the larger the possibility that the abnormal data exists in the sub-segment where the corresponding m-th characteristic value is located is, and the larger the value of the corresponding abnormal index coefficient is.
And thirdly, obtaining the comprehensive abnormality index of each position under each segment according to the abnormality index coefficient, the corresponding first sub-segment sequence and the corresponding second sub-segment sequence of each position under each segment.
The second sub-segment sequence at each position under each segment has a corresponding abnormality index coefficient, which reflects the condition that the environment detection data may have abnormality data under the segment, and further, the environment detection data may have a certain influence on the formaldehyde detection data, so that the comprehensive abnormality condition of all the environment detection data at each position under the segment can be more comprehensively reflected by analyzing the change condition of the data in the first sub-segment sequence and the second sub-segment sequence corresponding to each position under each segment and combining the abnormality condition corresponding to the environment detection data to obtain the comprehensive abnormality index.
Specifically, for any position of any segment, calculating the absolute value of the difference between the first data and the last data in the first sub-segment sequence to obtain the change amplitude of the first sub-segment sequence; for a second sub-segment sequence corresponding to any one of the environment detection data, calculating the absolute value of the difference between the first data and the last data in the second sub-segment sequence to obtain the change amplitude of the second sub-segment sequence; calculating the product of the abnormality index coefficient, the change amplitude and the preset influence degree super-parameter of the second sub-segment sequence at the position under the segmentation to obtain the influence degree coefficient of the environment detection data; calculating the sum value of influence coefficients of all environment detection data, taking the normalized value of the variation amplitude of the first sub-segment sequence and the absolute value of the difference value of the sum value as the comprehensive abnormal index at the position under the segment, and expressing the comprehensive abnormal index as follows by a formula:
Wherein, the liquid crystal display device comprises a liquid crystal display device,
represents the comprehensive abnormality index at the i-th position under the nth segment,
representing the magnitude of the change in the corresponding first sub-segment sequence at the i-th position under the n-th segment,
an abnormality index coefficient indicating a second sub-segment sequence corresponding to the nth segment of the a-th environment detection data at the ith position,
indicating the pre-set influence degree super-parameters corresponding to the a-th environment detection data,
representing the magnitude of the change in the sequence of the corresponding second sub-segment of the a-th environment detection data at the i-th position under the n-th segment,
representing the a-th environmental detection dataThe coefficient of influence of the degree of influence,
the number of kinds of environmental detection data, including four kinds of temperature, humidity, ethanol, and ammonia gas concentration in this embodiment, is represented, and norm () is a normalization function.
Degree of influence superparameter
The influence degree of the a-th environmental detection data on the formaldehyde detection data, namely, the influence degree super-parameter characterization changes the same degree on each environmental detection data, for example, when the temperature is increased by 20% like ammonia, wherein the two environmental detection data respectively change the formaldehyde content by 10% and 20% in the forward direction, the influence degree super-parameter obtained by taking the two parameters as quantization is respectively 0.5 and 1, and an influence degree super-parameter needs to be set by an implementer according to a specific implementation scene.
And step four, obtaining abnormal weights of each piece of data in the second time sequence at each position according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data in the corresponding second sub-segment sequence, carrying out filtering processing on the data in the second time sequence at each position according to the abnormal weights, and obtaining corrected formaldehyde detection data according to the environment detection data obtained by the filtering processing and the data in the first time sequence.
Firstly, it should be noted that, the second sub-segment sequence corresponding to each environmental detection data at each position under each segment has a corresponding abnormality index coefficient, and the possibility of having abnormal data in the corresponding second sub-segment sequence is reflected in terms of the data change trend in the second sub-segment sequence. The second sub-segment sequence corresponding to the plurality of environmental detection data at each position of each segment corresponds to one comprehensive abnormality index, and the possibility of abnormal data in the corresponding second sub-segment sequence is reflected in terms of the influence degree between the environmental detection data and the formaldehyde detection data.
Further, combining the abnormal data conditions of the two aspects, and simultaneously considering the change of each data in the second sub-segment sequence, analyzing the abnormal weight of each data, namely obtaining the abnormal weight of each data in the second time sequence at each position according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data under the corresponding segment.
Specifically, for a second sub-segment sequence at any position under any one segment, calculating the product of an abnormality index coefficient and a comprehensive abnormality index of the second sub-segment sequence; recording any one data in the second sub-segment sequence as selected data, calculating the absolute value of the difference between the selected data and the last data adjacent to the selected data, calculating the absolute value of the difference between the selected data and the next data adjacent to the selected data, and taking the normalized value of the product between the sum of the absolute values of the two differences and the product as the abnormal weight of the selected data; and further obtaining an abnormal weight for each data in the second time sequence at each position, wherein the selected data cannot be the endpoint value in the second time sequence, i.e. the selected data cannot be the first data and the last data in the second time sequence.
Specifically, if the selected data is the first data in the second time sequence, calculating the absolute value of the difference between the selected data and the next adjacent data, and taking the normalized value of the product between the two times of the absolute value of the difference and the product as the abnormal weight of the selected data. If the selected data is the last data in the second time sequence, calculating the absolute value of the difference between the selected data and the last data adjacent to the selected data, and taking the normalized value of the product between the two times of the absolute value of the difference and the product as the abnormal weight of the selected data. Meanwhile, it should be noted that, when the first data in the second sub-segment sequence is the selected data, the last data adjacent to the selected data can be obtained through the corresponding second time sequence.
In this embodiment, the data u in the two sub-segment sequence at the i-th position under the nth segment of the a-th environment detection data is described as the selected data, and the calculation formula of the abnormal weight of the selected data is specifically:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing the abnormal weight of the data u,
represents the comprehensive abnormality index at the i-th position under the nth segment,
an abnormality index coefficient indicating a second sub-segment sequence corresponding to the nth segment of the a-th environment detection data at the ith position, 
Representing a second corresponding to the a-th environment detection data under the n-th segment at the i-th positionThe sum of absolute values of differences corresponding to the data u and two adjacent data in the sub-segment sequence, and norm () is a normalization function.
According to the method for calculating the abnormal weight, the abnormal weight of each data in the second time sequence corresponding to each environmental data can be obtained, and then the weight of the data in the second time sequence during filtering can be adjusted based on the abnormal weight, so that the filtering result is accurate, the filtering result cannot be influenced by the abnormal data, and the greater influence on the corrected formaldehyde detection data is avoided.
Specifically, filtering processing is performed on the data in the second time sequence at each position according to the abnormal weights, and filtering processing is performed on the data in the second time sequence by using a preset filtering window, wherein the filtering weight of the central data in the filtering window is the difference between the value 1 and the abnormal weight corresponding to the data, and the filtering weights of other data in the filtering window are the abnormal weights corresponding to the data.
When the abnormal weight of the central data of the filtering window is larger, the possibility that the central data is the abnormal data is higher, so that the filtering weight corresponding to the central data in the filtering window is smaller, the filtering weight corresponding to other data is larger, and the degree of retaining the abnormal data characteristics of the central data is smaller and the degree of being smoothed is larger after the central data is filtered. When the abnormal weight of the central data of the filtering window is smaller, the possibility that the central data is the abnormal data is smaller, so that the filtering weight corresponding to the central data in the filtering window is larger, the filtering weight corresponding to other data is smaller, the degree of retaining the abnormal data characteristic of the central data is larger, and the degree of being smoothed is smaller. The data information loss caused by the indiscriminate mean filtering of the normal data is correspondingly reduced.
In this embodiment, each data in the second time sequence at each position of each environmental detection data is used as central data, and filtering processing is performed by using a preset filtering window, where the length of the filtering window is 9, and an implementer can set according to a specific implementation scenario.
And finally, obtaining corrected formaldehyde detection data according to the environment detection data obtained by filtering and the data in the first time sequence. In this embodiment, the corrected formaldehyde detection data is obtained based on the environmental detection data and the formaldehyde detection data obtained after the filtering process in combination with the cross interference suppression algorithm. The formaldehyde detection data is modified by using the environmental detection data, which is a known technique and will not be described in detail herein. For example, in the paper titled Zhuojuan, entitled multi-sensor based formaldehyde detection system and cross-interference suppression studies thereof, a specific correction method is disclosed.
In summary, the filtering weight of each environmental detection data is obtained according to the change characteristics of the environmental detection data and the formaldehyde detection data by combining the data characteristics of the scene. Firstly, according to the periodic change characteristics of environment detection data and the abnormal condition of the data, analyzing the abnormal condition of the environment detection data to obtain a corresponding abnormal index coefficient, and further according to the deviation degree of the change of formaldehyde detection data in trend data and the data change under the common influence of each environment detection data, analyzing the whole abnormal condition of the environment detection data by combining the abnormal condition of the environment detection data. Finally, by combining the anomaly analysis of the two aspects, the anomaly weight of each environment detection data is obtained, and the corresponding filtering weight in the mean value filtering process is adjusted, so that the normal data has more self data characteristics when being filtered, the loss of data information is reduced, and the corrected formaldehyde detection data is more accurate.
Claims (7)
1. The method for processing the formaldehyde detection data of the decorative material is characterized by comprising the following steps of:
acquiring a first time sequence corresponding to formaldehyde detection data at different positions and a second time sequence corresponding to environment detection data, and segmenting the first time sequence and the second time sequence to obtain a first sub-segment sequence and a second sub-segment sequence under each segment;
Obtaining an abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-segment sequence corresponding to any position under each segment and the second sub-segment sequences corresponding to other positions and the abnormal condition of the data in the second sub-segment sequence;
obtaining a comprehensive abnormality index at each position of each segment according to the abnormality index coefficient, the corresponding first sub-segment sequence and the corresponding second sub-segment sequence at each position of each segment;
obtaining abnormal weights of each data in the second time sequence at each position according to the abnormal index coefficient, the comprehensive abnormal index and the difference condition of the data in the corresponding second sub-segment sequence, carrying out filtering processing on the data in the second time sequence at each position according to the abnormal weights, and obtaining corrected formaldehyde detection data according to the environment detection data obtained by the filtering processing and the data in the first time sequence.
2. The method for processing formaldehyde detection data of decorative material according to claim 1, wherein the obtaining the abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-segment sequence corresponding to any position under each segment and the second sub-segment sequences corresponding to other positions and the abnormality condition of the data in the second sub-segment sequences specifically comprises:
STL decomposition is carried out on the second time sequence, a periodic sequence corresponding to a second sub-segment sequence obtained through decomposition is recorded as a second sub-periodic sequence, and a residual sequence corresponding to the second sub-segment sequence obtained through decomposition is recorded as a second sub-residual sequence;
and obtaining an abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-period sequence corresponding to the second sub-segment sequence at any position under each segment and the second sub-period sequences corresponding to the second sub-segment sequences at other positions and the residual value in the second sub-residual sequence corresponding to the second sub-segment sequence.
3. The method for processing formaldehyde detection data of decorative materials according to claim 2, wherein obtaining the abnormality index coefficient of the second sub-segment sequence corresponding to each position under each segment according to the difference between the second sub-period sequence corresponding to the second sub-segment sequence at any position under each segment and the second sub-period sequences corresponding to the second sub-segment sequences at other positions, and residual data in the second sub-residual sequences corresponding to the second sub-segment sequences, specifically comprises:
marking any one position as a target position, for a second sub-segment sequence at the target position under any one segment,
Recording any one characteristic value in a second sub-period sequence corresponding to the second sub-period sequence as a target characteristic value, and calculating the average value of the absolute value of the difference value between the target characteristic value and each characteristic value in the second sub-period sequence corresponding to the second sub-period sequence at other positions to obtain the characteristic difference degree of the target characteristic value; the characteristic value is a normalized value of a crest value or a trough value;
in a second sub-period sequence corresponding to the second sub-segment sequence, taking a data point with a data value being a first preset value as a partition point, dividing the second sub-period sequence into at least two sub-segments by utilizing the partition point, and acquiring a characteristic value corresponding to each sub-segment and a residual value corresponding to each sub-segment in a second sub-residual sequence;
calculating the sum of all residual values under the sub-segments corresponding to the target characteristic value to obtain an abnormality index of the target characteristic value;
taking the product of the characteristic difference degree and the abnormality degree index of the target characteristic value as an abnormality index of the target characteristic value; taking the normalized value of the sum of the abnormality indexes of all the characteristic values as the abnormality index coefficient of the corresponding second sub-segment sequence at the target position under the segment.
4. The method for processing formaldehyde detection data of decorative materials according to claim 1, wherein the obtaining the comprehensive abnormality index at each position of each segment according to the abnormality index coefficient, the corresponding first sub-segment sequence and the corresponding second sub-segment sequence at each position of each segment, specifically comprises:
Calculating the absolute value of the difference between the first data and the last data in the first sub-segment sequence at any position of any segment to obtain the change amplitude of the first sub-segment sequence;
for a second sub-segment sequence corresponding to any one of the environment detection data, calculating the absolute value of the difference between the first data and the last data in the second sub-segment sequence to obtain the change amplitude of the second sub-segment sequence; calculating the product of the abnormality index coefficient, the change amplitude and the preset influence degree super-parameter of the second sub-segment sequence at the position under the segmentation to obtain the influence degree coefficient of the environment detection data;
and calculating the sum value of influence coefficients of all environment detection data, and taking the normalized value of the variation amplitude of the first sub-segment sequence and the absolute value of the difference value of the sum value as the comprehensive abnormal index at the position under the segment.
5. The method for processing formaldehyde detection data of decorative material according to claim 1, wherein the obtaining the abnormal weight of each data in the second time sequence at each position according to the abnormality index coefficient, the comprehensive abnormality index and the difference condition of the data in the corresponding second sub-segment sequence specifically comprises:
For a second sub-segment sequence at any position under any one segment, calculating the product of an abnormality index coefficient and a comprehensive abnormality index of the second sub-segment sequence;
recording any one data in the second sub-segment sequence as selected data, calculating the absolute value of the difference between the selected data and the last data adjacent to the selected data, calculating the absolute value of the difference between the selected data and the next data adjacent to the selected data, and taking the normalized value of the product between the sum of the absolute values of the two differences and the product as the abnormal weight of the selected data; obtaining abnormal weight of each data in the second time sequence at each position; the selected data cannot be an endpoint in the second timing sequence.
6. The method for processing formaldehyde detection data of decorative material according to claim 1, wherein the segmenting the first time sequence and the second time sequence to obtain the first sub-segment sequence and the second sub-segment sequence under each segment specifically comprises:
for any one first time sequence, taking each peak value and each valley value of data in the first time sequence as a segmentation point, segmenting the first time sequence, and obtaining a first sub-segment sequence under each segmentation;
And for any one second time sequence, acquiring data points in the second time sequence at the same time as the segmentation point, and segmenting the second time sequence by the data points to obtain a second sub-segment sequence under each segmentation.
7. The method for processing formaldehyde detection data for decorative materials according to claim 1, wherein the filtering processing of the data in the second time series at each position according to the abnormal weight is specifically:
and filtering the data in the second time sequence by using a preset filtering window, wherein the filtering weight of the central data in the filtering window is the difference value between the numerical value 1 and the abnormal weight corresponding to the data, and the filtering weights of other data in the filtering window are the abnormal weights corresponding to the data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310388990.XA CN116108008A (en) | 2023-04-13 | 2023-04-13 | Decorative material formaldehyde detection data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310388990.XA CN116108008A (en) | 2023-04-13 | 2023-04-13 | Decorative material formaldehyde detection data processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116108008A true CN116108008A (en) | 2023-05-12 |
Family
ID=86267619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310388990.XA Withdrawn CN116108008A (en) | 2023-04-13 | 2023-04-13 | Decorative material formaldehyde detection data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116108008A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116366069A (en) * | 2023-06-02 | 2023-06-30 | 菏泽鹏远混凝土有限公司 | High-performance concrete proportioning data processing method |
| CN116414076A (en) * | 2023-06-12 | 2023-07-11 | 济宁长兴塑料助剂有限公司 | Intelligent monitoring system for recovered alcohol production data |
| CN116582134A (en) * | 2023-07-11 | 2023-08-11 | 江苏盖亚环境科技股份有限公司 | Drilling and testing integrated equipment data processing method |
| CN116881646A (en) * | 2023-09-06 | 2023-10-13 | 山东奥晶生物科技有限公司 | Stevioside production monitoring data management system |
| CN116878590A (en) * | 2023-09-06 | 2023-10-13 | 山东远联信息科技有限公司 | Intelligent service collaborative operation management system |
| CN116911621A (en) * | 2023-09-13 | 2023-10-20 | 山东尚儒弘毅精细化工有限公司 | Intelligent assessment method and system for resin production safety risk based on data driving |
| CN117316301A (en) * | 2023-11-22 | 2023-12-29 | 北华大学 | Intelligent compression processing method for gene detection data |
| CN117349611A (en) * | 2023-12-06 | 2024-01-05 | 山东清控生态环境产业发展有限公司 | Water quality fluctuation instrument monitoring method based on big data analysis |
| CN117760593A (en) * | 2024-02-22 | 2024-03-26 | 张家港江海粮油港务有限公司 | Abnormal monitoring method for storage temperature of grain crops |
| CN117829381A (en) * | 2024-03-05 | 2024-04-05 | 成都农业科技职业学院 | Agricultural greenhouse data optimization acquisition system based on Internet of things |
| CN117871466A (en) * | 2024-03-12 | 2024-04-12 | 苏州安易得安全科技有限公司 | Laser methane detector for monitoring data self-checking |
| CN118010939A (en) * | 2024-04-10 | 2024-05-10 | 山东华检检测有限公司 | Intelligent formaldehyde detection method |
| CN118070195A (en) * | 2024-04-16 | 2024-05-24 | 山东艾克索仑电气有限公司 | Mining alternating current frequency converter abnormal data state monitoring system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472404A (en) * | 2018-10-31 | 2019-03-15 | 山东大学 | A kind of Short-Term Load Forecasting of Electric Power System, model, apparatus and system |
| CN109655518A (en) * | 2019-02-25 | 2019-04-19 | 珠海格力电器股份有限公司 | Formaldehyde electrochemical sensing detection device, calibration method and purifier |
| CN110851338A (en) * | 2019-09-23 | 2020-02-28 | 平安科技（深圳）有限公司 | Abnormality detection method, electronic device, and storage medium |
| CN111324639A (en) * | 2020-02-11 | 2020-06-23 | 京东数字科技控股有限公司 | Data monitoring method and device and computer readable storage medium |
| CN112198209A (en) * | 2019-06-23 | 2021-01-08 | 宁波方太厨具有限公司 | Formaldehyde detection method and formaldehyde detection device |
| US20210253738A1 (en) * | 2018-07-11 | 2021-08-19 | The United States Of America, As Represented By The Secretary, Department Of Health And Human Servic | Monoclonal antibody for the detection of the antiretroviral drug emtricitabine (ftc, 2',3'-dideoxy-5-fluoro-3'-thiacytidine) |
| CN113342610A (en) * | 2021-06-11 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Time sequence data anomaly detection method and device, electronic equipment and storage medium |
| CN115659284A (en) * | 2022-12-27 | 2023-01-31 | 河北新龙科技集团股份有限公司 | Big data fusion platform |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
-
2023
- 2023-04-13 CN CN202310388990.XA patent/CN116108008A/en not_active Withdrawn
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210253738A1 (en) * | 2018-07-11 | 2021-08-19 | The United States Of America, As Represented By The Secretary, Department Of Health And Human Servic | Monoclonal antibody for the detection of the antiretroviral drug emtricitabine (ftc, 2',3'-dideoxy-5-fluoro-3'-thiacytidine) |
| CN109472404A (en) * | 2018-10-31 | 2019-03-15 | 山东大学 | A kind of Short-Term Load Forecasting of Electric Power System, model, apparatus and system |
| CN109655518A (en) * | 2019-02-25 | 2019-04-19 | 珠海格力电器股份有限公司 | Formaldehyde electrochemical sensing detection device, calibration method and purifier |
| CN112198209A (en) * | 2019-06-23 | 2021-01-08 | 宁波方太厨具有限公司 | Formaldehyde detection method and formaldehyde detection device |
| CN110851338A (en) * | 2019-09-23 | 2020-02-28 | 平安科技（深圳）有限公司 | Abnormality detection method, electronic device, and storage medium |
| CN111324639A (en) * | 2020-02-11 | 2020-06-23 | 京东数字科技控股有限公司 | Data monitoring method and device and computer readable storage medium |
| CN113342610A (en) * | 2021-06-11 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Time sequence data anomaly detection method and device, electronic equipment and storage medium |
| CN115659284A (en) * | 2022-12-27 | 2023-01-31 | 河北新龙科技集团股份有限公司 | Big data fusion platform |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
Non-Patent Citations (2)
| Title |
|---|
| QINGSONG WEN，等: "Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns", 《KDD \'20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING》, pages 2203 * |
| 苏卫星，等: "时间序列异常点及突变点的检测算法", 《计算机研究与发展》, vol. 51, no. 4, pages 781 - 788 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116366069A (en) * | 2023-06-02 | 2023-06-30 | 菏泽鹏远混凝土有限公司 | High-performance concrete proportioning data processing method |
| CN116366069B (en) * | 2023-06-02 | 2023-08-08 | 菏泽鹏远混凝土有限公司 | High-performance concrete proportioning data processing method |
| CN116414076A (en) * | 2023-06-12 | 2023-07-11 | 济宁长兴塑料助剂有限公司 | Intelligent monitoring system for recovered alcohol production data |
| CN116414076B (en) * | 2023-06-12 | 2023-08-15 | 济宁长兴塑料助剂有限公司 | Intelligent monitoring system for recovered alcohol production data |
| CN116582134A (en) * | 2023-07-11 | 2023-08-11 | 江苏盖亚环境科技股份有限公司 | Drilling and testing integrated equipment data processing method |
| CN116582134B (en) * | 2023-07-11 | 2023-10-13 | 江苏盖亚环境科技股份有限公司 | Drilling and testing integrated equipment data processing method |
| CN116881646A (en) * | 2023-09-06 | 2023-10-13 | 山东奥晶生物科技有限公司 | Stevioside production monitoring data management system |
| CN116878590A (en) * | 2023-09-06 | 2023-10-13 | 山东远联信息科技有限公司 | Intelligent service collaborative operation management system |
| CN116881646B (en) * | 2023-09-06 | 2023-11-21 | 山东奥晶生物科技有限公司 | Stevioside production monitoring data management system |
| CN116878590B (en) * | 2023-09-06 | 2023-11-21 | 山东远联信息科技有限公司 | Intelligent service collaborative operation management system |
| CN116911621A (en) * | 2023-09-13 | 2023-10-20 | 山东尚儒弘毅精细化工有限公司 | Intelligent assessment method and system for resin production safety risk based on data driving |
| CN116911621B (en) * | 2023-09-13 | 2023-12-05 | 山东尚儒弘毅精细化工有限公司 | Intelligent assessment method and system for resin production safety risk based on data driving |
| CN117316301A (en) * | 2023-11-22 | 2023-12-29 | 北华大学 | Intelligent compression processing method for gene detection data |
| CN117316301B (en) * | 2023-11-22 | 2024-03-05 | 北华大学 | Intelligent compression processing method for gene detection data |
| CN117349611A (en) * | 2023-12-06 | 2024-01-05 | 山东清控生态环境产业发展有限公司 | Water quality fluctuation instrument monitoring method based on big data analysis |
| CN117349611B (en) * | 2023-12-06 | 2024-03-08 | 山东清控生态环境产业发展有限公司 | Water quality fluctuation instrument monitoring method based on big data analysis |
| CN117760593A (en) * | 2024-02-22 | 2024-03-26 | 张家港江海粮油港务有限公司 | Abnormal monitoring method for storage temperature of grain crops |
| CN117760593B (en) * | 2024-02-22 | 2024-05-10 | 张家港江海粮油港务有限公司 | Abnormal monitoring method for storage temperature of grain crops |
| CN117829381A (en) * | 2024-03-05 | 2024-04-05 | 成都农业科技职业学院 | Agricultural greenhouse data optimization acquisition system based on Internet of things |
| CN117829381B (en) * | 2024-03-05 | 2024-05-14 | 成都农业科技职业学院 | Agricultural greenhouse data optimization acquisition system based on Internet of things |
| CN117871466A (en) * | 2024-03-12 | 2024-04-12 | 苏州安易得安全科技有限公司 | Laser methane detector for monitoring data self-checking |
| CN117871466B (en) * | 2024-03-12 | 2024-05-24 | 苏州安易得安全科技有限公司 | Laser methane detector for monitoring data self-checking |
| CN118010939A (en) * | 2024-04-10 | 2024-05-10 | 山东华检检测有限公司 | Intelligent formaldehyde detection method |
| CN118070195A (en) * | 2024-04-16 | 2024-05-24 | 山东艾克索仑电气有限公司 | Mining alternating current frequency converter abnormal data state monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116108008A (en) | Decorative material formaldehyde detection data processing method | |
| US20140149325A1 (en) | System monitor and method of system monitoring | |
| CN116320042B (en) | Internet of things terminal monitoring control system for edge calculation | |
| CN116718218B (en) | Test data processing method for photoelectric integrated sensing chip | |
| CN117540238B (en) | Data security management method for industrial digital information acquisition device | |
| CN117434153B (en) | Road nondestructive testing method and system based on ultrasonic technology | |
| CN117112514B (en) | Recording and storing method based on p-chloromethyl styrene production data | |
| CN117196353A (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN117454096A (en) | Motor production quality detection method and system | |
| CN117783745A (en) | Data online monitoring method and system for battery replacement cabinet | |
| CN117668684A (en) | Power grid electric energy data anomaly detection method based on big data analysis | |
| CN115081331A (en) | Wind turbine generator running state abnormity detection method based on state parameter reconstruction error | |
| CN115113233A (en) | Laser radar cloud layer detection method based on bidirectional reconstruction backscatter signals | |
| CN112416661B (en) | Multi-index time sequence anomaly detection method and device based on compressed sensing | |
| CN110702786B (en) | Beam structure damage identification method based on multi-scale singular attractor prediction error | |
| CN117109487A (en) | Automatic nondestructive measurement method for metal thickness | |
| CN116879409A (en) | Analysis and detection method for fruit damage based on gas sensor | |
| Boriah et al. | A Comparative Study Of Algorithms For Land Cover Change. | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN112184778B (en) | Short-term displacement detection method based on GNSS dynamic positioning time sequence segmentation | |
| CN114114400A (en) | Microseism event effective signal pickup method | |
| Pardasani et al. | Quantitative assessment of respiratory distress using convolutional neural network for multivariate time series segmentation | |
| CN117874434B (en) | Data cleaning method in intelligent environmental temperature and humidity detection process | |
| CN113598810B (en) | Automatic fetal heart rate baseline calculation method based on segmentation network | |
| CN116448062B (en) | Bridge settlement deformation detection method, device, computer 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230512 |