CN116414076B - Intelligent monitoring system for recovered alcohol production data - Google Patents

Intelligent monitoring system for recovered alcohol production data Download PDF

Info

Publication number
CN116414076B
CN116414076B CN202310685390.XA CN202310685390A CN116414076B CN 116414076 B CN116414076 B CN 116414076B CN 202310685390 A CN202310685390 A CN 202310685390A CN 116414076 B CN116414076 B CN 116414076B
Authority
CN
China
Prior art keywords
data
sequence
temperature
liquid level
difference
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
Application number
CN202310685390.XA
Other languages
Chinese (zh)
Other versions
CN116414076A (en
Inventor
王庆康
王华振
岳远阳
刘勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Changxing Plastic Additives Co ltd
Original Assignee
Jining Changxing Plastic Additive Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jining Changxing Plastic Additive Co ltd filed Critical Jining Changxing Plastic Additive Co ltd
Priority to CN202310685390.XA priority Critical patent/CN116414076B/en
Publication of CN116414076A publication Critical patent/CN116414076A/en
Application granted granted Critical
Publication of CN116414076B publication Critical patent/CN116414076B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G05B19/0428—Safety, monitoring
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/24—Pc safety
    • G05B2219/24024—Safety, surveillance
    • 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
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Investigating Or Analyzing Materials Using Thermal Means (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent monitoring system for recovering alcohol production data, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory so as to realize the following steps: acquiring a temperature time sequence and a liquid level time sequence and a subsequence in a time period of the production process of the recovered alcohol; acquiring the abnormality degree of data, and dividing the temperature time sequence and the liquid level time sequence to obtain a first temperature sequence and a first liquid level sequence; obtaining importance according to the difference and change conditions between the data in the first temperature sequence and the first liquid level sequence and the abnormality degree of the data; and obtaining the weight of each production data according to the distribution characteristics and the importance degree of each production data, encoding the production data by using Huffman encoding according to the weight, and taking the encoded production data as monitoring data. The invention can obtain better data compression effect.

Description

Intelligent monitoring system for recovered alcohol production data
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent monitoring system for recovery of alcohol production data.
Background
The recovered alcohol is a biofuel extracted from waste, and the waste is crushed, dried, sieved and the like, and then is put into a reactor for fermentation and distillation to obtain the ethanol with higher purity. In the production equipment and the process, the intelligent monitoring system for the production data of the recovered alcohol detects and records the production data in real time through the sensor, stores the collected production data in the cloud database, and provides a series of data analysis and visualization tools for real-time analysis and prediction of the production data, so that the production efficiency and quality of the production of the recovered alcohol are improved.
However, long-time data monitoring can generate massive data, and a large storage space is required, so that in order to improve the utilization rate of the storage space, high-efficiency compression processing is required to be performed on the acquired production data. When the traditional Huffman coding is used for coding production data in the production process of the recovered alcohol, because the occurrence probability of normal data in the production process of the recovered alcohol is larger, shorter coding data can be given, the occurrence probability of abnormal production data is smaller, longer coding data can be given, and therefore, when the important abnormal production data is stored and transmitted, the situation that data is lost or decoding errors easily occurs is caused, the effect of processing the recovered alcohol production data by the traditional Huffman coding is poorer, and the follow-up data analysis result of the monitoring data is possibly inaccurate.
Disclosure of Invention
In order to solve the technical problem of poor treatment effect on the recovered alcohol production data by utilizing the traditional Huffman coding, the invention aims to provide an intelligent monitoring system for the recovered alcohol production data, which adopts the following technical scheme:
the invention provides an intelligent monitoring system for recovered alcohol production data, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory so as to realize the following steps:
acquiring temperature data and liquid level data in a time period of a production process of recovered alcohol to form a temperature time sequence, a liquid level time sequence and a subsequence, wherein the subsequence comprises a temperature subsequence and a liquid level subsequence;
obtaining the abnormality degree of the data in each subsequence according to the change speed and the fluctuation degree of the data in each subsequence; dividing the temperature time sequence and the liquid level time sequence simultaneously by utilizing all the temperature subsequences or the liquid level subsequences to obtain a first temperature sequence and a first liquid level sequence;
obtaining the importance degree of each production data in the production process time length corresponding to the first temperature sequence and the first liquid level sequence according to the difference and the change condition between the data in the first temperature sequence and the first liquid level sequence and the abnormality degree of the data;
And obtaining the weight of each production data according to the distribution characteristics and the importance degree of each production data in different production process time lengths, encoding the production data by utilizing Huffman encoding according to the weight, and taking the encoded production data as monitoring data.
Preferably, the obtaining the abnormality degree of the data in each sub-sequence according to the change speed and the fluctuation degree of the data in each sub-sequence is specifically:
for any one sub-sequence, taking the ratio of the range of the data in the sub-sequence to the corresponding time length of the sub-sequence as the variation characteristic index of the sub-sequence;
calculating the absolute value of the difference between two adjacent data in the subsequence to obtain a first difference sequence, calculating the difference between the two adjacent data in the first difference sequence to obtain a second difference sequence, and forming different difference data segments by data corresponding to each continuous same data type in the second difference sequence;
obtaining a state factor of the subsequence according to the number of the difference data segments in the subsequence and the difference between the data in the second difference sequence; and obtaining the degree of abnormality of the data in the subsequence according to the change characteristic index of the subsequence, the number of the difference data segments and the state factor.
Preferably, the state factor for obtaining the subsequence according to the number of the difference data segments in the subsequence and the difference between the data in the second difference sequence is specifically:
if the second difference sequence corresponding to the subsequence only comprises one difference data segment, the value of the state factor of the subsequence is a first preset value;
if the second difference sequence corresponding to the subsequence comprises two or more difference data segments, marking the average value of all data in the difference data segments as the characteristic average value of the difference data segments for any one difference data segment contained in the second difference sequence; and calculating the average value of the absolute values of the differences between the characteristic average values of every two adjacent differential data segments in the second differential sequence, carrying out normalization processing on the average value of the absolute values of the differences, and taking the sum value of the numerical value obtained by the normalization processing and the first preset value as the state factor of the subsequence.
Preferably, the obtaining the degree of abnormality of the data in the subsequence according to the variation characteristic index of the subsequence, the number of the difference data segments and the state factor is specifically:
taking any one sub-sequence as a target sub-sequence, acquiring the frequency of the change characteristic indexes of the target sub-sequence in the change characteristic indexes of all the sub-sequences, and taking the difference value between a second preset value and the frequency as a first coefficient; the all subsequences and the target subsequence are temperature subsequences or liquid level subsequences;
Obtaining the product between the number of the difference data segments contained in the second difference sequence corresponding to the target subsequence and the state factor of the target subsequence, and taking the normalized value of the product as a second coefficient;
obtaining the degree of abnormality of the data in the target subsequence according to the first coefficient, the second coefficient and the change characteristic index of the target subsequence; the first coefficient, the second coefficient and the change characteristic index are in positive correlation with the degree of abnormality.
Preferably, the obtaining the importance degree of each production data in the production process time length corresponding to the first temperature sequence and the first liquid level sequence according to the difference, the change condition and the abnormality degree of the data in the first temperature sequence and the first liquid level sequence specifically includes:
for any first temperature sequence and first liquid level sequence corresponding to the time sequence, respectively carrying out normalization processing on data in the first temperature sequence and the first liquid level sequence to obtain a second temperature sequence and a second liquid level sequence; calculating a difference value between the second temperature sequence and corresponding position data in the second liquid level sequence to obtain a difference value sequence, and obtaining the number of extreme points in the difference value sequence;
if the intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, taking the difference value between the number of the extreme points and a third preset value as a first characteristic value; the third preset value is smaller than the number of extreme points; if no intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, the number of extreme points is used as a first characteristic value;
Obtaining a third coefficient according to the abnormal degree of the data in the first temperature sequence and the first liquid level sequence, obtaining a difference data segment corresponding to the second temperature sequence and the second liquid level sequence, and obtaining a fourth coefficient according to the difference data segment corresponding to the second temperature sequence or the second liquid level sequence and the first characteristic value;
recording the production process time length corresponding to the first temperature sequence and the first liquid level sequence as a target time period, and taking a data sequence consisting of temperature data, liquid level data and other production data in the alcohol recovery production process in the target time period as a production data sequence;
taking the product between the normalized values of the third coefficient and the fourth coefficient as the importance degree of each data in each production data sequence in the target time period.
Preferably, the third coefficient is specifically obtained according to the abnormality degree of the data in the first temperature sequence and the first liquid level sequence:
if the first temperature sequence and the first liquid level sequence are obtained by segmentation based on the temperature subsequence, marking any one data in the first liquid level sequence as selected data, and acquiring the ratio of the time length corresponding to the difference data segment where the selected data are located to the time length corresponding to the first liquid level sequence as the time sequence duty ratio of the selected data; weighting and summing the abnormality degree of each data in the first liquid level sequence by using the time sequence duty ratio to obtain the characteristic abnormality degree corresponding to the first liquid level sequence;
And taking the average value of the normalized value of the abnormality degree of the data in the first temperature sequence and the normalized value of the characteristic abnormality degree average value as a third coefficient.
Preferably, the obtaining the fourth coefficient according to the difference data segment corresponding to the second temperature sequence or the second liquid level sequence and the first characteristic value specifically includes:
and obtaining a normalized value of the first characteristic value corresponding to the second liquid level sequence, and calculating the product of the normalized value and the number of the difference data segments in the second liquid level sequence to obtain a fourth coefficient.
Preferably, the weight of each production data obtained according to the distribution characteristics and the importance degree of each production data in different production process time lengths is specifically:
and for any one production data sequence, taking any one data as the marking data, acquiring the average value of importance degrees corresponding to all data with the same value as the marking data to obtain a first index, taking the probability of occurrence of the marking data in all data with the same production data as the marking data as a second index, and obtaining the weight of the marking data according to the first index and the second index.
Preferably, the method for acquiring the temperature subsequence and the liquid level subsequence specifically comprises the following steps:
For the temperature time sequence, acquiring an extreme value of temperature data in the temperature time sequence, and dividing the temperature time sequence by taking the extreme value of the temperature data as a temperature data dividing point to obtain different temperature subsequences;
and for the liquid level time sequence, acquiring an extremum of liquid level data in the liquid level time sequence, and dividing the liquid level time sequence by taking the extremum of the liquid level data as a liquid level data dividing point to obtain different liquid level subsequences.
Preferably, the encoding the production data by huffman coding according to the weights specifically comprises:
and arranging all the production data according to the sequence from the large weight to the small weight, constructing a Huffman tree according to the arrangement sequence, and encoding the production data by using the Huffman tree.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, the temperature data and the liquid level data in the time period of the production process of the recovered alcohol are firstly obtained to form the temperature time sequence, the liquid level time sequence and the corresponding subsequences, so that the subsequent analysis of the data change conditions of the temperature data and the liquid level data is convenient, and the importance index with accurate production data can be obtained. Then, the change speed and the fluctuation degree of the data in each subsequence are analyzed to obtain the abnormality degree of the data, the abnormality degree of the data is used for representing the possibility of the abnormality condition of the data, and then the subsequence is used for simultaneously dividing the temperature time sequence and the liquid level time sequence, so that a first temperature sequence and a first liquid level sequence with the same data length can be obtained, and the subsequent analysis of the difference condition between the temperature data and the liquid level data is more accurate. Further, the difference, the change condition and the abnormal degree of the data in the first temperature sequence and the first liquid level sequence are analyzed, the importance degree of the production data is obtained, and the importance degree of the production data in the time length of the corresponding production process can be evaluated by analyzing the change condition of the temperature data and the liquid level data and the relevance between the change condition of the temperature data and the liquid level data. Finally, the importance degree of the production data is utilized to obtain the weight corresponding to the production data, huffman coding is carried out on the production data based on the weight, a better data compression effect can be obtained, and further the monitoring result of the data is 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 performed by an intelligent monitoring system for recovering alcohol production data in accordance with an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of an intelligent monitoring system for recovering alcohol production data according to the invention by combining 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 intelligent monitoring system for recovering alcohol production data provided by the invention with reference to the accompanying drawings.
The specific scene aimed by the invention is as follows: the long-time data monitoring can generate massive data, a large storage space is needed, and in order to improve the utilization rate of the storage space, high-efficiency compression processing is needed for the collected production data. The conventional Huffman coding constructs a Huffman tree according to the occurrence probability of each data, the coding length corresponding to the data with larger occurrence probability is shorter, and the coding length corresponding to the data with smaller occurrence probability is longer, thereby realizing the compression processing of the data. The occurrence probability of abnormal production data in the process of recovering alcohol is small, and longer coding data can be given, so that the situation that data loss or decoding errors occur due to the influence of noise, network fluctuation and other interference is easy to occur when important abnormal production data are stored and transmitted.
The invention provides an intelligent monitoring system for recovering alcohol production data, which is used for realizing the steps shown in figure 1, and comprises the following specific steps:
Step one, acquiring temperature data and liquid level data in a time period of a production process of recovered alcohol to form a temperature time sequence, a liquid level time sequence and a subsequence, wherein the subsequence comprises a temperature subsequence and a liquid level subsequence.
There are various types of time series data, such as temperature, pressure, liquid level, pH, and oxygen content, in the recovered alcohol production equipment and process during the recovered alcohol production process time period. As the most critical process in the process of recycling alcohol is fermentation, the pretreated waste is put into a reactor, and a proper amount of microorganisms and enzymes are added to convert organic matters such as carbohydrate and protein in the waste into ethanol and other nutrient substances. Therefore, the embodiment of the invention analyzes the temperature data and the liquid level data of the reactor and acquires the importance degree of different time series data in the period of the production process of the recovered alcohol.
Specifically, the temperature data of each moment in the recovery alcohol production process time period is obtained to form a temperature time sequence, and the liquid level data of each moment in the recovery alcohol production process time period is obtained to form a liquid level time sequence. In this embodiment, the time length of the time period of the alcohol recovery process is set to be the time length corresponding to the whole alcohol recovery process, the time interval between two adjacent moments is set to be 5min, and the implementer can set according to the specific implementation scenario.
Further, a subsequence corresponding to the temperature time sequence and the liquid level time sequence is obtained, wherein the subsequence comprises a temperature subsequence and a liquid level subsequence, namely the temperature time sequence and the liquid level time sequence are respectively segmented to obtain a corresponding subsequence, the subsequence corresponding to the temperature time sequence is called a temperature subsequence, and the subsequence corresponding to the liquid level time sequence is called a liquid level subsequence.
Specifically, for a temperature time sequence, acquiring an extremum of temperature data in the temperature time sequence, and dividing the temperature time sequence by taking the extremum of the temperature data as a temperature data dividing point to obtain different temperature subsequences; and for the liquid level time sequence, acquiring an extremum of liquid level data in the liquid level time sequence, and dividing the liquid level time sequence by taking the extremum of the liquid level data as a liquid level data dividing point to obtain different liquid level subsequences.
For the temperature time sequence, curve fitting can be performed on all temperature data in the temperature time sequence, so that extreme points on a fitting curve are obtained, the extreme points are used as temperature data dividing points to segment the fitting curve, and all temperature data corresponding to one segment form a temperature subsequence. According to the same method, a plurality of liquid level subsequences corresponding to the liquid level time sequence can be obtained.
It should be noted that, the method for obtaining the fitting curve and the extreme point is a known technique, and will not be described herein. In this embodiment, the temperature data or the liquid level data corresponding to the extreme point only exist in one sub-sequence, and the practitioner can choose to place the temperature data or the liquid level data corresponding to the extreme point in the preceding or following sub-sequence according to the specific implementation scenario. It will be appreciated that for all temperature data, all temperature sub-sequences are arranged in time order to form a temperature time series sequence, and similarly, all liquid level sub-sequences are arranged in time order to form a liquid level time series sequence.
Step two, obtaining the abnormal degree of the data in each subsequence according to the change speed and the fluctuation degree of the data in each subsequence; and simultaneously dividing the temperature time sequence and the liquid level time sequence by utilizing all the temperature subsequences or the liquid level subsequences to obtain a first temperature sequence and a first liquid level sequence.
The recovery of alcohol production is a multi-cycle process, in the fermentation process, the temperature of the reactor needs to be kept in a proper range to ensure the normal growth and metabolism of fermenting microorganisms, meanwhile, the liquid level in the reactor needs to be kept in a proper range to ensure the uniform mixing and stability of fermentation liquid, and the temperature and liquid level change is stable, so that the fermentation effect can be ensured to be stable, and further, whether the data in each subsequence has abnormal conditions or not can be analyzed according to the change speed and fluctuation degree of the data in each subsequence.
The subsequences include a temperature subsequence and a liquid level subsequence, and in this embodiment, the temperature subsequence is described as an example, and a method for acquiring the degree of abnormality of data in the subsequence is described in detail.
Firstly, the time length corresponding to each temperature sub-sequence is recorded as the time period of the temperature sub-sequence, the change trend of the temperature data in each time period is presented as an ascending or descending trend, and the change speed of the temperature data in the time period corresponding to the temperature sub-sequence can be obtained according to the change condition of the temperature data.
Specifically, for any one temperature sub-sequence, the ratio between the range of the temperature data in the temperature sub-sequence and the time length corresponding to the temperature sub-sequence is used as the variation characteristic index of the temperature sub-sequence. The range of the temperature data in the temperature sub-sequence is the difference between the maximum value and the minimum value of all the temperature data in the temperature sub-sequence. And characterizing the change speed of the temperature data in the temperature subsequence by utilizing the ratio of the maximum difference of the temperature data in the temperature subsequence to the time length, namely the change characteristic index.
Due to the fact thatThe temperature during the recovery of alcohol needs to be kept within a suitable range, so that analysis of the variation of temperature data in the time series of temperatures is required. For any one temperature sub-sequence, calculating the absolute value of the difference between two adjacent data in the temperature sub-sequence to obtain a first difference sequence, which is expressed as Wherein C is a first differential sequence, </i >>Representing first data in a first sequence of differences, and (2)>Representing the second data in the first sequence of differences,represents the m-1 st data in the first differential sequence, m represents the total number of temperature data contained in the temperature sub-sequence. In the present embodiment, the absolute value of the difference between any one of the temperature data in the temperature sub-sequence and the next-to-next temperature data is taken as the data in the first difference sequence.
Calculating the difference between two adjacent data in the first difference sequence to obtain a second difference sequence, which is further expressed asWherein->For the second difference sequence, +.>Representing the first data in the second sequence of differences, and (2)>Representing second data in a second sequence of differences, and (2)>Represents the mth in the second difference sequence-2 data, m representing the total number of temperature data contained in the temperature sub-sequence. In this embodiment, the difference between any one data in the first difference sequence and the next data adjacent thereto is taken as the data in the second difference sequence.
The data in the second difference sequence can represent the change condition of the difference between the temperature data in the temperature sub-sequence, namely, the change speed condition of the temperature data is reflected. The negative data in the second difference sequence indicates that the corresponding temperature data is in a descending state of ascending or descending speed in the ascending or descending process, namely, the changing speed of the temperature data is gradually slowed down. The data of 0 in the second difference sequence indicates that the corresponding temperature data is in a uniform change state in the rising or falling process, that is, the change speed of the temperature data is uniform. The data in the second difference sequence is positive to indicate that the corresponding temperature data is in an ascending or descending speed increasing state in the ascending or descending process, namely the change speed of the temperature data is gradually increased.
And constructing different differential data segments by data corresponding to each continuous same data type in the second differential sequence, for example, judging from the first data in the second differential sequence, if the first data and the second data are the same in data type, placing the first data and the second data in the same differential data segment, continuously judging whether the second data and the third data are the same in data type, if so, placing the second data and the third data in the same differential data segment, wherein the differential data segment comprises the first data, the second data and the third data in the second differential sequence. If the first difference data segment and the second difference data segment are different, a first difference data segment contained in the second difference sequence is obtained, the first data segment and the second data segment are contained, a new difference data segment is formed by starting from the third data segment, and the like, until all the data in the second difference sequence are placed, and then stopping.
It should be noted that, the difference data segment may be one data, and meanwhile, in this embodiment, the data type of the data in the second difference sequence represents the sign characteristic of the data, that is, the same data type represents that the values of the data are both positive, both negative, or both 0. The data within the same differential data segment has the same state of variation.
Further, by analyzing the speed of the change of the temperature data, the state factor of the temperature sub-sequence is obtained, namely, the state factor of the temperature sub-sequence is obtained according to the number of the difference data segments in the temperature sub-sequence and the difference between the data in the second difference sequence.
Specifically, if the second difference sequence corresponding to the temperature sub-sequence only includes one difference data segment, it is indicated that there is only one change state of the temperature data in the temperature sub-sequence, and further it is indicated that the temperature data is in a relatively uniform change degree, and then the value of the state factor of the temperature sub-sequence is a first preset value. In this embodiment, the value of the first preset value is 1, and the implementer can set according to a specific implementation scenario.
If the second difference sequence corresponding to the temperature sub-sequence comprises two or more difference data segments, the condition that the temperature data in the temperature sub-sequence has multiple change states is indicated, the more the number of the difference data segments is, the more the state change times of the temperature data is indicated, the more the change state fluctuation of the temperature data is further indicated, and the greater the possibility that the corresponding temperature data has abnormality is indicated.
Then, for any one of the difference data segments contained in the second difference sequence, marking the average value of all data in the difference data segment as the characteristic average value of the difference data segment; calculating the average value of the absolute values of the differences between the characteristic average values of every two adjacent differential data segments in the second differential sequence, carrying out normalization processing on the average value of the absolute values of the differences, taking the sum value of the numerical value obtained by the normalization processing and the first preset value as the state factor of the temperature subsequence, wherein the calculation formula of the state factor can be expressed as follows:
Wherein,,status factor representing the z-th temperature sub-sequence，/>Representing the number of pieces of difference data, which the second difference sequence corresponding to the z-th temperature sub-sequence contains,/for each piece of difference data>Representing the characteristic mean value of the ith differential data segment contained in the second differential sequence corresponding to the z-th temperature subsequence,/th differential data segment>Representing the characteristic mean value of the (i+1) th difference data segment contained in the second difference sequence corresponding to the z-th temperature sub-sequence, and representing the normalization function by Norm ().
The difference between the characteristic average values of two adjacent difference data segments in the second difference sequence corresponding to the z-th temperature subsequence reflects the magnitude of fluctuation of the temperature data change state, and the larger the value is, the larger the temperature change magnitude in the temperature subsequence is, the greater the possibility that the temperature data in the corresponding temperature subsequence has abnormal conditions is, and the larger the value of the corresponding state factor is. The state factor of the temperature sub-sequence characterizes fluctuations in the state of variation of the temperature data in the temperature sub-sequence.
Finally, the abnormal degree of the temperature data in the temperature sub-sequence is obtained by combining the change speed of the temperature data in the temperature sub-sequence, the fluctuation condition of the change state and the occurrence times of the state change, namely, the abnormal degree of the temperature data in the temperature sub-sequence is obtained according to the change characteristic index of the temperature sub-sequence, the number of the difference data segments and the state factor.
Specifically, any one subsequence is used as a target subsequence, the frequency of occurrence of the change characteristic index of the target subsequence in the change characteristic indexes of all the subsequences is obtained, and the difference value between the second preset value and the frequency is used as a first coefficient; the all subsequences and the target subsequence are temperature subsequences or liquid level subsequences; obtaining the product between the number of the difference data segments contained in the second difference sequence corresponding to the target subsequence and the state factor of the target subsequence, and taking the normalized value of the product as a second coefficient; obtaining the degree of abnormality of the data in the target subsequence according to the first coefficient, the second coefficient and the change characteristic index of the target subsequence; the first coefficient, the second coefficient and the change characteristic index are in positive correlation with the degree of abnormality.
In this embodiment, taking the z-th temperature sub-sequence as the target sub-sequence, the calculation formula of the degree of abnormality of the data in the target sub-sequence may be expressed as:
wherein,,indicating the degree of abnormality of the z-th temperature subsequence,/->Indicating the number of times the change characteristic index of the z-th temperature sub-sequence appears in the change characteristic indexes of all the temperature sub-sequences,/->Represents the total number of temperature subsequences, < > >Status factor representing the z-th temperature sub-sequence,/->Representing the number of pieces of difference data, which the second difference sequence corresponding to the z-th temperature sub-sequence contains,/for each piece of difference data>Representing the variation characteristic index of the z-th temperature sub-sequence, norm () represents the normalization function,representing the normalized value of the second coefficient.
The frequency of occurrence of the change characteristic index of the z-th temperature sub-sequence in the change characteristic indexes of all the temperature sub-sequences is reflected by the frequency of occurrence of the change speed of the temperature data in the temperature sub-sequences in all the temperature sub-sequences,the larger the frequency is, the smaller the corresponding value of the first coefficient is, which indicates that the change speed of the temperature data in the z-th temperature sub-sequence is the general case of the change speed of the whole data, and the smaller the corresponding value of the abnormality degree is, which indicates that the possibility of the abnormality of the temperature data in the temperature sub-sequence is smaller.
The larger the value of (c) is, the faster the temperature data in the temperature sub-sequence rises or falls, and the larger the corresponding abnormality degree is, and the greater the possibility that the temperature data is abnormal at this time is. />As a second factor, there are three different states of speed change during the rising or falling of temperature data, ++ >The larger the value of (c) is, the more the number of times the state indicating the change of speed is alternately appeared, the higher the fluctuation frequency of the state indicating the change of temperature data is, the larger the value of the state factor is, and the larger the fluctuation amplitude of the state indicating the change of temperature data is. The second coefficient represents the influence degree of temperature data when the temperature data change state fluctuates, and the larger the corresponding value of the second coefficient is, the larger the corresponding value of the abnormality degree is, so that the greater the possibility of abnormality of the temperature data is.
It should be noted that, the elements in each temperature sub-sequence are temperature data at different moments, and then the degree of abnormality of the data in each temperature sub-sequence is the degree of abnormality of each temperature data. Similarly, elements in each liquid level sub-sequence are liquid level data at different moments, and the abnormal degree of the data in each liquid level sub-sequence is the abnormal degree of each liquid level data.
Thus, the degree of abnormality of the temperature data and the degree of abnormality of the liquid level data corresponding to each time can be obtained.
It can be understood that each temperature sub-sequence is obtained by dividing based on the data change characteristic of the temperature time sequence, each liquid level sub-sequence is obtained by dividing based on the data change characteristic of the liquid level time sequence, and therefore, the time length corresponding to each temperature sub-sequence may not be equal, or there may be a situation that the time length corresponding to each temperature sub-sequence is partially equal, or there may be a situation that the time length corresponding to each liquid level sub-sequence is not equal, so that in order to facilitate the analysis of the change relation between different production data in the same time period, the temperature time sequence and the liquid level time sequence need to be divided again.
And simultaneously dividing the temperature time sequence and the liquid level time sequence by utilizing all the temperature subsequences or the liquid level subsequences to obtain a first temperature sequence and a first liquid level sequence, wherein the temperature time sequence corresponds to a plurality of first temperature sequences, and the liquid level time sequence corresponds to a plurality of first liquid level sequences. The dividing mode of the temperature subsequence can be attached to the data change condition of the temperature time sequence, and the dividing mode of the liquid level subsequence is attached to the data change condition of the liquid level time sequence, so that if the change condition of the liquid level data is analyzed along with the temperature data change, the temperature subsequence is utilized to divide the temperature time sequence and the liquid level time sequence at the same time. If the change condition of the temperature data is analyzed along with the change of the liquid level data, the temperature time sequence and the liquid level time sequence are simultaneously segmented by utilizing the liquid level subsequence.
In this embodiment, the temperature sub-sequence is utilized to divide the temperature time sequence and the liquid level time sequence simultaneously to obtain a first temperature sequence and a first liquid level sequence, specifically, the time length corresponding to each temperature sub-sequence is obtained, then according to the time length corresponding to each temperature sub-sequence, liquid level data corresponding to the same time length is obtained in the liquid level time sequence to form different first liquid level sequences, and similarly, the first temperature sequences are obtained, it is understood that the first temperature sequences are identical to the temperature data in the corresponding temperature sub-sequences, and meanwhile, each first temperature sequence has a first liquid level sequence corresponding to the first temperature sequence, that is, the time lengths of the first temperature sequences corresponding to each other are equal to the time length of the first liquid level sequence.
And thirdly, obtaining the importance degree of each production data in the production process time length corresponding to the first temperature sequence and the first liquid level sequence according to the difference and the change condition between the data in the first temperature sequence and the first liquid level sequence and the abnormality degree of the data.
The abnormality degree of each temperature data is obtained based on the change condition of the temperature data in the reactor in the process of producing the recovered alcohol, the abnormality degree of each liquid level data is obtained based on the change condition of the liquid level data in the reactor in the process of producing the recovered alcohol, and various production data in the fermentation reactor are related and mutually influenced, in the same production process time period, one production data is normal data, other production data is abnormal data, and the normal data can be known to be data identification errors according to the relevance between the data, so that the subsequent data compression storage is influenced. Therefore, there is a need to further analyze the correlation between different kinds of production data.
In this example, since temperature data and liquid level data are the two production data critical in the fermentation reactor, the correlation between temperature data and liquid level data was analyzed. When the temperature in the reactor increases, the evaporation rate of the fermentation broth increases, resulting in a decrease in the liquid level, while when the temperature in the reactor decreases, the liquid density increases, while the volume of the fermentation broth remains substantially unchanged, so that the liquid level increases as the temperature decreases, i.e. there is a certain inverse relationship between the temperature data and the liquid level data.
In order to analyze the data change condition between the first temperature sequence and the first liquid level sequence by eliminating the influence of dimension, normalization processing is needed to be carried out on the temperature data in the first temperature sequence and the liquid level data in the first liquid level sequence to obtain a second temperature sequence and a second liquid level sequence. It can be understood that the second temperature sequences are normalized sequences of the first temperature sequences, and the second liquid level sequences are normalized sequences of the first liquid level sequences, so that each second temperature sequence also has a corresponding second liquid level sequence.
Corresponding to any one of the second temperature sequences, obtaining a second liquid level sequence corresponding to the second temperature sequence in time sequence, calculating a difference value between the second temperature sequence and corresponding position data in the second liquid level sequence to obtain a difference value sequence, in the embodiment, recording data in the second temperature sequence as second temperature data, recording data in the second liquid level sequence as second liquid level data, further calculating a difference value between the second temperature data corresponding to each moment and the second liquid level data within a time length corresponding to the second temperature sequence and the second liquid level sequence, and forming the difference value sequence.
The number of extreme points in the difference sequence is acquired, specifically, when the correlation between the temperature data and the liquid level data is normal, there are two cases in which the number of extreme points in the difference sequence is two. If no intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, the data in the difference sequence is changed to be increased or decreased, and only two local extreme points exist, namely the first data and the last data in the difference sequence. If the intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, the data change in the difference sequence is continuously decreased after continuous increasing or continuously increased after continuous decreasing, and three local extremum points exist at the moment.
When the correlation between the temperature data and the liquid level data is abnormal, the change between the temperature data and the liquid level data is complex, the fluctuation degree of the data in the difference sequence is large, and the number of local extreme points in the difference sequence is large.
Based on the above, in order to avoid that the difference in the number of extreme points in the difference sequence under normal conditions further affects the accuracy of performing abnormal analysis on the data, the first characteristic value is obtained based on the number of extreme points in the difference sequence, when an intersection exists between the value range of all the data in the second temperature sequence and the value range of all the data in the second liquid level sequence, the number of extreme points in the difference sequence is limited, so that the number of extreme points corresponding to the difference sequence is kept consistent when no intersection exists between the value range of all the data in the second temperature sequence and the value range of all the data in the second liquid level sequence.
Specifically, if an intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, taking the difference value between the number of extreme points and a third preset value as a first characteristic value; the third preset value is smaller than the number of extreme points; if no intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, the number of extreme points is used as a first characteristic value; wherein, the value of the third preset value is 1.
And recording the production process time length corresponding to the first temperature sequence and the first liquid level sequence as a target time period, and taking a data sequence consisting of temperature data, liquid level data and other production data in the production process of recovering the alcohol in the target time period as a production data sequence. That is, in the target time period, each time corresponds to one temperature data, one liquid level data and other production data, the other production data can be pressure, pH value, oxygen content and the like, meanwhile, the temperature data and the liquid level data can also be called as production data, and each production data at each time in the target time period is further formed into a data sequence and recorded as a production data sequence.
Finally, the importance degree of each production data at each moment in the whole target time period is obtained by analyzing the association relation between the temperature data and the liquid level data change in the target time period and combining the abnormality degree of the temperature data and the liquid level data. Obtaining a third coefficient according to the abnormality degree of the data in the first temperature sequence and the first liquid level sequence, obtaining a difference data segment corresponding to the second temperature sequence and the second liquid level sequence, and obtaining a fourth coefficient according to the difference data segment corresponding to the second temperature sequence or the second liquid level sequence and the first characteristic value; taking the product between the normalized values of the third coefficient and the fourth coefficient as the importance degree of each data in each production data sequence in the target time period.
Specifically, if the first temperature sequence and the first liquid level sequence are obtained by dividing based on the temperature subsequence, recording any one data in the first liquid level sequence as selected data, and obtaining the ratio of the time length corresponding to the difference data segment where the selected data is located to the time length corresponding to the first liquid level sequence as the time sequence duty ratio of the selected data; weighting and summing the abnormality degree of each data in the first liquid level sequence by using the time sequence duty ratio to obtain the characteristic abnormality degree corresponding to the first liquid level sequence; and taking the average value of the normalized value of the abnormality degree of the data in the first temperature sequence and the normalized value of the characteristic abnormality degree average value as a third coefficient. And obtaining a normalized value of the first characteristic value corresponding to the second liquid level sequence, and calculating the product of the normalized value and the number of the difference data segments in the second liquid level sequence to obtain a fourth coefficient.
In this embodiment, since the temperature time series sequence and the liquid level time series sequence are simultaneously divided based on the temperature sub-sequence, it is necessary to adjust the degree of abnormality of the data in the first liquid level sequence obtained by the division by the change condition of the data in the first liquid level sequence. Therefore, when calculating the third coefficient, the weight needs to be obtained according to the change condition of the data in the first liquid level sequence, the abnormality degree of each data in the first liquid level sequence is weighted and summed, and when calculating the fourth coefficient, the number of different data segments in the first liquid level sequence needs to be counted.
In other embodiments, if the temperature time series sequence and the liquid level time series sequence are simultaneously divided based on the liquid level sub-sequence, the degree of abnormality of the data in the first temperature sequence obtained by the division needs to be adjusted by the change condition of the data in the first temperature sequence. Therefore, when calculating the third coefficient, the weight needs to be obtained according to the change condition of the data in the first temperature sequence, the difference degree of each data in the first temperature sequence is weighted and summed, and when calculating the fourth coefficient, the number of different data segments in the first temperature sequence needs to be counted.
Specifically, in this embodiment, taking an example of dividing the temperature time sequence and the liquid level time sequence simultaneously by using the temperature subsequence to obtain a first temperature sequence and a first liquid level sequence, taking a production process time length corresponding to a u-th first temperature sequence and a u-th first liquid level sequence as a target time period, and taking a v-th data in the first liquid level sequence as selected data, a calculation formula of importance degree of each data in each production data sequence in the target time period may be expressed as follows:
wherein,,representing the importance degree corresponding to the target time period; / >A normalized value representing the degree of abnormality of the data in the target time period, i.e., a normalized value of the degree of abnormality of the temperature data in the u-th first temperature sequence; />The abnormal degree of the v-th liquid level data in the target time period is represented, namely the abnormal degree of the v-th data in the u-th first liquid level sequence is represented, namely the abnormal degree of the selected data; />Indicating the time length of the difference data segment where the v-th liquid level data is located within the target time segment,/->Time length representing the target time period, +.>Representing the total number of liquid level data contained in the target period, that is, the total number of times contained in the target period; />Representing a first characteristic value corresponding to the target time period, < >>Representing the number of different data segments contained in the second liquid level sequence corresponding to the target time segment, norm () is a normalization function. It should be noted that, in the embodiment of the present invention, the normalization processing is performed by using a maximum value and minimum value normalization method, and an implementer may set according to a specific implementation scenario.
Is a third coefficient>Representing the time-sequence duty cycle of the v-th data in the u-th first liquid level sequence, i.e. the time-sequence duty cycle of the selected data,/->The characteristic abnormality degree of the u-th first liquid level sequence is represented. The time sequence proportion of the selected data reflects the time length proportion of the difference data section where the selected data is located, the duration of the selected data in the ascending or descending state is represented, the greater the time sequence proportion is, the longer the duration of the data change state is, the more important the corresponding selected data is, the greater the weight needs to be given to the corresponding selected data, and then the degree of abnormality of the data in the first temperature data sequence and the degree of abnormality of the data in the first liquid level sequence are combined in the same target time section to obtain a third coefficient, and the third coefficient can represent the degree of abnormality of each production data in the target time section. The larger the value of the third coefficient is, the greater the possibility of abnormality of the data is, and the greater the corresponding importance degree is.
The method for acquiring the degree of abnormality of the data in the second step is known as a temperature subAll temperature data in the sequence correspond to the same degree of abnormality, and all liquid level data in a liquid level sub-sequence correspond to the same degree of abnormality, so that the method is utilizedA normalized value representing the degree of abnormality corresponding to the temperature data in a first temperature sequence. While at the same time->The normalized value of the abnormality degree corresponding to the liquid level data in the adjusted first liquid level sequence can be represented, and the abnormality degree corresponding to each production data in the target time period can be obtained by obtaining the average value of the normalized value and the normalized value.
For the fourth coefficient, the first characteristic value +.>The larger the value of the data sequence is, the greater the possibility of abnormality in the corresponding data in the target time period is, and the greater the importance of the corresponding data is. The number of differential data segments contained in the second liquid level sequence corresponding to the target time period +.>The larger the value is, the more the change state of the temperature in the target time period possibly causes the change state of various liquid level data, the greater the possibility of abnormality of the data in the target time period is, the greater the importance of the corresponding data is, and the normalized data is utilized >For->The adjustment can represent the abnormal condition of the correlation between the temperature data and the liquid level data in the target time period, and the larger the value of the fourth coefficient is, the greater the possibility of abnormality is, and the greater the corresponding importance degree is.
It should be noted that, the difference data segment is obtained by dividing the sub-sequence based on the variation condition of the difference between the data in the sub-sequence, when the temperature sub-sequence is utilized to re-divide the temperature time sequence and the liquid level time sequence, the difference data segment is not re-divided, for the first temperature sequence, each temperature data can find the difference data segment where it is located, for the first liquid level sequence, each liquid level data can also find the difference data segment where it is located, and the second liquid level sequence is obtained after the data normalization in the first liquid level sequence, then the data in the second liquid level sequence can also find the difference data segment where it is located.
The importance degree corresponding to the target time period characterizes the importance degree of the data corresponding to each moment of all production data in the target time period, for example, when the production data is pressure data, the importance degree of the pressure data at each moment in the target time period is the same, and the importance degrees are all . It can be understood that a target time period corresponds to a value of an importance level, that is, the importance level of production data of all kinds and all times in the target time period is the same, that is, the importance of the recovery of the alcohol reactor in the corresponding time period is obtained by analyzing the change condition and the difference condition of the two kinds of data.
To this end, the importance degree of each production data can be obtained.
And step four, obtaining the weight of each production data according to the distribution characteristics and the importance degree of each production data in different production process time lengths, encoding the production data by utilizing Huffman encoding according to the weight, and taking the encoded production data as monitoring data.
In this embodiment, the important production data is given a larger weight by the importance degree of each production data, so that the huffman coding length is shorter, and the situation that the data is easy to be lost due to the overlong coding length of the important data can be avoided. The weight of each production data is obtained according to the distribution characteristics and the importance degree of each production data in different production process time lengths.
It should be noted that different time lengths of the production process correspond to different first temperature sequences and first liquid level sequences, so as to correspond to different importance degrees, and one or more data sequences formed by other production data, the first temperature sequences and the first liquid level sequences are collectively called as a production data sequence, and one production data sequence is a data sequence formed by one production data.
And analyzing any production data of any production process time length corresponding to any one of the first temperature sequences and the corresponding first liquid level sequences, namely taking any one of the production data sequences as marking data, acquiring the average value of importance degrees corresponding to all data with the same value as the marking data to obtain a first index, taking the probability of occurrence of the marking data in all data with the marking data as the same production data as a second index, and obtaining the weight of the marking data according to the first index and the second index.
In this embodiment, taking the target time period as an example, taking the x-th temperature data in the first temperature sequence as the tag data, the calculation formula of the weight of the tag data may be expressed as:
wherein,,weight value representing the xth temperature data in the first temperature sequence, < >>A first index corresponding to the xth temperature data in the first temperature sequence, namely a mean value representing the importance degree corresponding to the data with the same value as the xth temperature data in the first temperature sequence; />And the second index corresponding to the xth temperature data in the first temperature sequence is represented, namely the probability that the xth temperature data in the first temperature sequence appears in all the temperature data is represented.
The larger the value of the first index is, the larger the importance of the marking data is, the larger the value of the second index is, the larger the probability of occurrence of the marking data is, and further the importance of the marking data is, the larger the weight corresponding to the marking data is.
Further, the production data are encoded by utilizing Huffman coding according to the weight values, specifically, all the production data are arranged according to the order from big to small of the weight values, a Huffman tree is constructed according to the arrangement order, namely, two production data with the smallest weight value are acquired to form a binary tree, the sum value of the smallest two weight values is used as a new weight value, and then the construction process of the binary tree is repeated according to the new weight value and the weight values of other residual production data, until all the production data are placed in the binary tree, and the construction of the Huffman tree is completed. The right path in the huffman tree is encoded as 1 and the left path in the huffman tree is encoded as 0.
And encoding the production data by using the Huffman tree to obtain encoded data corresponding to each production data, and recording the encoded data as monitoring data corresponding to the production data. Finally, the relevant production manager can monitor the production data in the process of recovering the alcohol based on the monitoring data.
In other embodiments, the monitoring data can be transmitted to the cloud database for storage and analysis, the collected monitoring data is analyzed by using a big data analysis technology, and a manager can monitor and control the monitoring data in real time according to the analysis result.
In summary, the abnormal degree of the data is obtained by analyzing the data change trend of the temperature data and the liquid level data, and then the importance degree of the data is calculated according to the change relevance between the temperature data and the liquid level data and the abnormal degree, and then the weight of each production data is obtained by combining the occurrence probability of the data, and the weight of the production data with larger importance degree and larger occurrence probability is given based on the weight, so that the encoding length is shorter, the data compression effect is ensured, and meanwhile, the situation that the data is lost due to more important data is avoided.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.

Claims (4)

1. An intelligent monitoring system for recovering alcohol production data, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the following steps:
acquiring temperature data and liquid level data in a time period of a production process of recovered alcohol to form a temperature time sequence, a liquid level time sequence and a subsequence, wherein the subsequence comprises a temperature subsequence and a liquid level subsequence;
obtaining the abnormality degree of the data in each subsequence according to the change speed and the fluctuation degree of the data in each subsequence; dividing the temperature time sequence and the liquid level time sequence simultaneously by utilizing all the temperature subsequences or the liquid level subsequences to obtain a first temperature sequence and a first liquid level sequence;
obtaining the importance degree of each production data in the production process time length corresponding to the first temperature sequence and the first liquid level sequence according to the difference and the change condition between the data in the first temperature sequence and the first liquid level sequence and the abnormality degree of the data;
obtaining a weight of each production data according to the distribution characteristics and the importance degree of each production data in different production process time lengths, encoding the production data by utilizing Huffman encoding according to the weight, and taking the encoded production data as monitoring data;
The abnormal degree of the data in each subsequence obtained according to the change speed and the fluctuation degree of the data in each subsequence is specifically:
for any one sub-sequence, taking the ratio of the range of the data in the sub-sequence to the corresponding time length of the sub-sequence as the variation characteristic index of the sub-sequence;
calculating the absolute value of the difference between two adjacent data in the subsequence to obtain a first difference sequence, calculating the difference between the two adjacent data in the first difference sequence to obtain a second difference sequence, and forming different difference data segments by data corresponding to each continuous same data type in the second difference sequence;
obtaining a state factor of the subsequence according to the number of the difference data segments in the subsequence and the difference between the data in the second difference sequence; obtaining the degree of abnormality of the data in the subsequence according to the change characteristic index of the subsequence, the number of the difference data segments and the state factor;
the state factor of the subsequence obtained according to the number of the difference data segments in the subsequence and the difference between the data in the second difference sequence is specifically:
if the second difference sequence corresponding to the subsequence only comprises one difference data segment, the value of the state factor of the subsequence is a first preset value;
If the second difference sequence corresponding to the subsequence comprises two or more difference data segments, marking the average value of all data in the difference data segments as the characteristic average value of the difference data segments for any one difference data segment contained in the second difference sequence; calculating the average value of the absolute values of the differences between the characteristic average values of every two adjacent differential data segments in the second differential sequence, carrying out normalization processing on the average value of the absolute values of the differences, and taking the sum value of the numerical value obtained by the normalization processing and the first preset value as a state factor of the subsequence;
the abnormal degree of the data in the subsequence obtained according to the change characteristic index of the subsequence, the number of the difference data segments and the state factor is specifically as follows:
taking any one sub-sequence as a target sub-sequence, acquiring the frequency of the change characteristic indexes of the target sub-sequence in the change characteristic indexes of all the sub-sequences, and taking the difference value between a second preset value and the frequency as a first coefficient; the all subsequences and the target subsequence are temperature subsequences or liquid level subsequences;
obtaining the product between the number of the difference data segments contained in the second difference sequence corresponding to the target subsequence and the state factor of the target subsequence, and taking the normalized value of the product as a second coefficient;
Obtaining the degree of abnormality of the data in the target subsequence according to the first coefficient, the second coefficient and the change characteristic index of the target subsequence; the first coefficient, the second coefficient and the change characteristic index are in positive correlation with the degree of abnormality;
according to the difference and the change condition between the data in the first temperature sequence and the first liquid level sequence and the abnormality degree of the data, the importance degree of each production data in the production process time length corresponding to the first temperature sequence and the first liquid level sequence is obtained, and the method specifically comprises the following steps:
for any first temperature sequence and first liquid level sequence corresponding to the time sequence, respectively carrying out normalization processing on data in the first temperature sequence and the first liquid level sequence to obtain a second temperature sequence and a second liquid level sequence; calculating a difference value between the second temperature sequence and corresponding position data in the second liquid level sequence to obtain a difference value sequence, and obtaining the number of extreme points in the difference value sequence;
if the intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, taking the difference value between the number of the extreme points and a third preset value as a first characteristic value; the third preset value is smaller than the number of extreme points; if no intersection exists between the value ranges of all the data in the second temperature sequence and the value ranges of all the data in the second liquid level sequence, the number of extreme points is used as a first characteristic value;
Obtaining a third coefficient according to the abnormal degree of the data in the first temperature sequence and the first liquid level sequence, obtaining a difference data segment corresponding to the second temperature sequence and the second liquid level sequence, and obtaining a fourth coefficient according to the difference data segment corresponding to the second temperature sequence or the second liquid level sequence and the first characteristic value;
recording the production process time length corresponding to the first temperature sequence and the first liquid level sequence as a target time period, and taking a data sequence consisting of temperature data, liquid level data and other production data in the alcohol recovery production process in the target time period as a production data sequence;
taking the product between the normalized values of the third coefficient and the fourth coefficient as the importance degree of each data in each production data sequence in the target time period;
the third coefficient is specifically obtained according to the abnormality degree of the data in the first temperature sequence and the first liquid level sequence:
if the first temperature sequence and the first liquid level sequence are obtained by segmentation based on the temperature subsequence, marking any one data in the first liquid level sequence as selected data, and acquiring the ratio of the time length corresponding to the difference data segment where the selected data are located to the time length corresponding to the first liquid level sequence as the time sequence duty ratio of the selected data; weighting and summing the abnormality degree of each data in the first liquid level sequence by using the time sequence duty ratio to obtain the characteristic abnormality degree corresponding to the first liquid level sequence;
Taking the average value of the normalized value of the abnormal degree of the data in the first temperature sequence and the normalized value of the characteristic abnormal degree average value as a third coefficient;
the fourth coefficient obtained according to the difference data segment and the first characteristic value corresponding to the second temperature sequence or the second liquid level sequence specifically comprises:
and obtaining a normalized value of the first characteristic value corresponding to the second liquid level sequence, and calculating the product of the normalized value and the number of the difference data segments in the second liquid level sequence to obtain a fourth coefficient.
2. The intelligent monitoring system for recovering alcohol production data according to claim 1, wherein the weight of each production data obtained according to the distribution characteristics and the importance of each production data in different production process time lengths is specifically as follows:
and for any one production data sequence, taking any one data as the marking data, acquiring the average value of importance degrees corresponding to all data with the same value as the marking data to obtain a first index, taking the probability of occurrence of the marking data in all data with the same production data as the marking data as a second index, and obtaining the weight of the marking data according to the first index and the second index.
3. The intelligent monitoring system for recovering alcohol production data according to claim 1, wherein the acquisition method of the temperature subsequence and the liquid level subsequence comprises the following steps:
For the temperature time sequence, acquiring an extreme value of temperature data in the temperature time sequence, and dividing the temperature time sequence by taking the extreme value of the temperature data as a temperature data dividing point to obtain different temperature subsequences;
and for the liquid level time sequence, acquiring an extremum of liquid level data in the liquid level time sequence, and dividing the liquid level time sequence by taking the extremum of the liquid level data as a liquid level data dividing point to obtain different liquid level subsequences.
4. The intelligent monitoring system for recovering alcohol production data according to claim 1, wherein the encoding of the production data by huffman coding according to the weight is specifically:
and arranging all the production data according to the sequence from the large weight to the small weight, constructing a Huffman tree according to the arrangement sequence, and encoding the production data by using the Huffman tree.
CN202310685390.XA 2023-06-12 2023-06-12 Intelligent monitoring system for recovered alcohol production data Active CN116414076B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310685390.XA CN116414076B (en) 2023-06-12 2023-06-12 Intelligent monitoring system for recovered alcohol production data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310685390.XA CN116414076B (en) 2023-06-12 2023-06-12 Intelligent monitoring system for recovered alcohol production data

Publications (2)

Publication Number Publication Date
CN116414076A CN116414076A (en) 2023-07-11
CN116414076B true CN116414076B (en) 2023-08-15

Family

ID=87052963

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310685390.XA Active CN116414076B (en) 2023-06-12 2023-06-12 Intelligent monitoring system for recovered alcohol production data

Country Status (1)

Country Link
CN (1) CN116414076B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116757553B (en) * 2023-08-11 2023-11-21 山东中新农业发展有限公司 Agricultural organic waste resource utilization digital information management system
CN116913057B (en) * 2023-09-12 2023-12-01 西安中创博远网络科技有限公司 Livestock-raising abnormal early warning system based on thing networking
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
CN117493787B (en) * 2024-01-02 2024-03-15 山东力威液压技术有限公司 Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis
CN117928655B (en) * 2024-03-22 2024-07-05 济宁万生环保材料有限公司 Material reaction instant acid value data on-line monitoring system
CN118428245B (en) * 2024-07-04 2024-08-30 济宁玉园酿造食品有限公司 Intelligent temperature control method and system in disc starter propagation process

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005024562A2 (en) * 2003-08-11 2005-03-17 Eloret Corporation System and method for pattern recognition in sequential data
CN114429308A (en) * 2022-02-08 2022-05-03 河南鑫安利安全科技股份有限公司 Enterprise security risk assessment method and system based on big data
CN115219067A (en) * 2022-09-20 2022-10-21 金乡县成启仓储服务有限公司 Real-time state monitoring method for garlic storage
CN115801901A (en) * 2023-01-05 2023-03-14 安徽皖欣环境科技有限公司 Compression processing method for enterprise production emission data
CN115927770A (en) * 2022-11-01 2023-04-07 中冶南方工程技术有限公司 Real-time tracking method for tapping state of blast furnace
CN116108008A (en) * 2023-04-13 2023-05-12 山东明远生物科技有限公司 Decorative material formaldehyde detection data processing method
CN116183058A (en) * 2023-04-21 2023-05-30 实德电气集团有限公司 Monitoring method of intelligent capacitor
CN116208172A (en) * 2023-05-04 2023-06-02 山东阁林板建材科技有限公司 Data management system for building engineering project

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005024562A2 (en) * 2003-08-11 2005-03-17 Eloret Corporation System and method for pattern recognition in sequential data
CN114429308A (en) * 2022-02-08 2022-05-03 河南鑫安利安全科技股份有限公司 Enterprise security risk assessment method and system based on big data
CN115219067A (en) * 2022-09-20 2022-10-21 金乡县成启仓储服务有限公司 Real-time state monitoring method for garlic storage
CN115927770A (en) * 2022-11-01 2023-04-07 中冶南方工程技术有限公司 Real-time tracking method for tapping state of blast furnace
CN115801901A (en) * 2023-01-05 2023-03-14 安徽皖欣环境科技有限公司 Compression processing method for enterprise production emission data
CN116108008A (en) * 2023-04-13 2023-05-12 山东明远生物科技有限公司 Decorative material formaldehyde detection data processing method
CN116183058A (en) * 2023-04-21 2023-05-30 实德电气集团有限公司 Monitoring method of intelligent capacitor
CN116208172A (en) * 2023-05-04 2023-06-02 山东阁林板建材科技有限公司 Data management system for building engineering project

Also Published As

Publication number Publication date
CN116414076A (en) 2023-07-11

Similar Documents

Publication Publication Date Title
CN116414076B (en) Intelligent monitoring system for recovered alcohol production data
CN114428803B (en) Air compression station operation optimization method, system, storage medium and terminal
CN117332283B (en) Method and system for collecting and analyzing growth information of traditional Chinese medicinal materials
CN114169434A (en) Load prediction method
CN118114955B (en) Power scheduling method of virtual power plant and related equipment
CN111931834A (en) Method, equipment and storage medium for detecting abnormal flow data in aluminum profile extrusion process based on isolated forest algorithm
Kim et al. Tutorial on time series prediction using 1D-CNN and BiLSTM: A case example of peak electricity demand and system marginal price prediction
CN117473351B (en) Power supply information remote transmission system based on Internet of things
CN112200346B (en) Short-term wind power prediction method for weather fluctuation process division and matching
CN114722014A (en) Batch data time sequence transmission method and system based on database log file
CN118137479A (en) Short-term wind power prediction method based on combined prediction model
CN118037112A (en) Tread quality prediction model construction method based on data driving
CN114037143A (en) Short-term wind power combination prediction method
CN117808271A (en) Digital agricultural fertilizer data optimization management method and system
CN116757337B (en) House construction progress prediction system based on artificial intelligence
Hartanto et al. Stock Price Time Series Data Forecasting Using the Light Gradient Boosting Machine (LightGBM) Model
CN116384949B (en) Intelligent government affair information data management system based on digital management
CN110276478B (en) Short-term wind power prediction method based on segmented ant colony algorithm optimization SVM
CN116701846A (en) Hydropower station dispatching operation data cleaning method based on unsupervised learning
CN116894687A (en) Power consumption analysis method and system based on machine learning and electronic equipment
CN117134315A (en) Distribution transformer load prediction method and device based on BERT algorithm
CN116579120A (en) Synthetic method-based solar-wind power output sequence scene generation method
CN113792749A (en) Time series data abnormity detection method, device, equipment and storage medium
CN112767026A (en) Agricultural product price prediction method based on ARM-MLR
CN118412865B (en) Photovoltaic power station generated power prediction method based on complex weather

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
CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: No. 5 Chenyang Road, New Materials Industrial Park, Jining Canal Economic Development Zone, Rencheng District, Jining City, Shandong Province, 272053

Patentee after: Shandong Changxing Plastic Additives Co.,Ltd.

Address before: No. 5 Chenyang Road, New Materials Industrial Park, Jining Canal Economic Development Zone, Rencheng District, Jining City, Shandong Province, 272053

Patentee before: JINING CHANGXING PLASTIC ADDITIVE CO.,LTD.

PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An intelligent monitoring system for alcohol recovery production data

Granted publication date: 20230815

Pledgee: Jining Rushang Rural Bank Co.,Ltd. Nanzhang Branch

Pledgor: Shandong Changxing Plastic Additives Co.,Ltd.

Registration number: Y2024980003698