CN117408497A - Food processing material management and control method and system - Google Patents
Food processing material management and control method and system Download PDFInfo
- Publication number
- CN117408497A CN117408497A CN202311713472.7A CN202311713472A CN117408497A CN 117408497 A CN117408497 A CN 117408497A CN 202311713472 A CN202311713472 A CN 202311713472A CN 117408497 A CN117408497 A CN 117408497A
- Authority
- CN
- China
- Prior art keywords
- data
- sequence
- value
- main
- temperature
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 230000035772 mutation Effects 0.000 claims description 62
- 238000007726 management method Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 13
- 230000009191 jumping Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Manufacturing & Machinery (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a food processing material management and control method and system, comprising the following steps: acquiring temperature data of different areas in a food processing material storage warehouse within a period of time to obtain a plurality of temperature time sequence data sequences, acquiring a sudden change value of each temperature data to obtain the jumping degree of each temperature data, and acquiring an isolated value of each temperature data according to the distance between the temperature data and the sudden change value of the temperature data in all the temperature time sequence data to obtain a weight coefficient of each temperature data, thereby performing weighted average filtering processing to obtain an air conditioner start-stop instruction in the warehouse. According to the invention, the denoising effect of the temperature time sequence data sequence is improved through the weight coefficient of the self-adaptive temperature data, and accurate and reliable temperature data is obtained, so that an accurate control instruction is obtained, and the effect of controlling the food processing material pipe is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a food processing material management and control method and system.
Background
When food processing materials are delivered, strict quality inspection including aspects of appearance, smell, taste and the like is required, and relevant information is recorded on the materials passing the quality inspection. Conventionally, storage is generally established for material management and control, and storage environment information, such as temperature and humidity, is collected by setting up a plurality of monitoring points in the storage, so that storage conditions of the material are mastered in real time, and material deterioration caused by damp, high temperature and the like is prevented. However, due to the limitation of the sensor, noise interference is easy to occur in the collected data, and a weighted average filtering algorithm is often used for noise filtering at present.
The existing problems are as follows: for temperature data of a material storage environment, besides noise interference, certain fluctuation characteristics exist, certain information is often existing in fluctuation of the temperature data when the temperature fluctuation data participate in data trend analysis, when the weight selection in a weighted average filtering algorithm is inappropriate, the temperature data can be easily smoothed out as a conventional noise signal, information loss of raw data can be caused, the reliability of temperature data analysis results is further reduced, and therefore the effect of controlling food processing material management is reduced.
Disclosure of Invention
The invention provides a food processing material management and control method and a system, which aim to solve the existing problems.
The invention relates to a food processing material management and control method and a system, which adopt the following technical scheme:
one embodiment of the invention provides a method for controlling food processing materials, comprising the steps of:
in a food processing material storage warehouse, acquiring temperature data of different areas in the warehouse within a period of time to obtain a plurality of temperature time sequence data sequences; recording any one temperature time sequence data sequence as a target sequence; recording any one temperature data in the target sequence as main data; obtaining a mutation value of the main data according to the difference between the main data and the adjacent data in the target sequence;
in the target sequence, according to the difference and mutation value of the main data and the surrounding temperature data, obtaining the jump degree of the main data;
the temperature time sequence data sequence which is not the target sequence is marked as a control sequence; obtaining a local similarity coefficient of main data when the target sequence is matched with each control sequence according to the distance between the target sequence and the temperature data in each control sequence and the mutation value of the temperature data; obtaining an isolated value of the main data according to the local similarity coefficient of the main data when the target sequence is matched with all the comparison sequences;
obtaining a weight coefficient of the main data according to the isolated value of the main data and the jump degree of the main data; and obtaining an air conditioner start-stop instruction in the food processing material storage warehouse according to the weight coefficients of all the temperature data in all the temperature time sequence data sequences.
Further, according to the difference between the main data and the adjacent data in the target sequence, a specific calculation formula corresponding to the mutation value of the main data is obtained as follows:
wherein A is the mutation value of the main data, B is the data value of the main data,for the data value of the preceding temperature data adjacent to the main data in the target sequence, +.>For the data value of the next temperature data adjacent to the main data in the target sequence, ||is an absolute function, |is +.>Is a linear normalization function.
Further, in the target sequence, according to the difference and the mutation value of the main data and the surrounding temperature data, the jump degree of the main data is obtained, which comprises the following specific steps:
in the target sequence, the main data, a sequence segment formed by L temperature data before the main data and L temperature data after the main data are recorded as a reference sequence segment corresponding to the main data; the L is a preset quantity threshold value;
recording each temperature data in the reference sequence segment as reference data;
and obtaining the jump degree of the main data according to the data values and the mutation values of all the reference data.
Further, the specific calculation formula corresponding to the jump degree of the main data is obtained according to the data values and the mutation values of all the reference data:
where C is the degree of jump of the main data, n is the number of reference data,for the data value of the ith reference data,for the mean value of the data values of all reference data, +.>Is the mutation value of the ith reference data.
Further, according to the distance between the target sequence and the temperature data in each control sequence and the mutation value of the temperature data, the local similarity coefficient of the main data when the target sequence is matched with each control sequence is obtained, and the method comprises the following specific steps:
the ordinal value of the main data in the target sequence is marked as a main ordinal value;
marking any one control sequence as a main control sequence;
the temperature data corresponding to the main ordinal value in the main comparison sequence is marked as comparison main data;
in the main comparison sequence, a sequence segment formed by comparison main data, L temperature data before the comparison main data and L temperature data after the comparison main data is recorded as a comparison sequence segment corresponding to the comparison main data;
obtaining a distance value sequence corresponding to the reference sequence segment and the comparison sequence segment by using a DTW algorithm; each distance value in the distance value sequence corresponds to one temperature data in the reference sequence section and one temperature data in the comparison sequence section;
in the distance value sequence, recording a mutation value of one temperature data in a reference sequence section corresponding to each distance value as a main mutation value of each distance value; recording the mutation value of one temperature data in the control sequence section corresponding to each distance value as a mutation value of each distance value;
and obtaining the local similarity coefficient of the main data when the target sequence is matched with the main control sequence according to all the distance values in the distance value sequence, the main mutation values and the mutation values.
Further, according to all the distance values in the distance value sequence and the main mutation values and the sub-mutation values thereof, a specific calculation formula corresponding to the local similarity coefficient of the main data when the target sequence is matched with the main control sequence is obtained as follows:
wherein D is a local similarity coefficient of the main data when the target sequence is matched with the main control sequence, m is the number of distance values in the distance value sequence,for the j-th distance value in the sequence of distance values, for example>Is the main mutation value of the j-th distance value in the distance value sequence, <>Is the mutation value of the j-th distance value in the distance value sequence.
Further, the obtaining the isolated value of the main data according to the local similarity coefficient of the main data when the target sequence is matched with all the control sequences comprises the following specific steps:
and (3) marking the average value of the local similarity coefficients of the main data when the target sequence is matched with all the control sequences as an isolated value of the main data.
Further, the step of obtaining the weight coefficient of the main data according to the isolated value of the main data and the jump degree of the main data comprises the following specific steps:
calculating the product of the isolated value and the jump degree of the main data, calculating the normalized value of the product, and recording one minus the normalized value as the weight coefficient of the main data.
Further, the method for obtaining the air conditioner start-stop instruction in the food processing material storage warehouse according to the weight coefficients of all the temperature data in all the temperature time sequence data comprises the following specific steps:
according to the weight coefficients of all temperature data in the target sequence, filtering and denoising the target sequence by using a weighted average filtering algorithm to obtain a denoising data sequence of the target sequence;
and transmitting the denoising data sequences of all the temperature time sequence data sequences to a warehouse management system to obtain an air conditioner start-stop instruction in the food processing material storage warehouse.
The invention also provides a food processing material management and control system, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the food processing material management and control method.
The technical scheme of the invention has the beneficial effects that:
in the embodiment of the invention, temperature data of different areas in a food processing material storage warehouse in a period of time are acquired to obtain a plurality of temperature time sequence data sequences, and a mutation value of each temperature data is acquired to obtain the jump degree of each temperature data. According to the method, whether noise interference exists in a local range is determined through data analysis of the local range of each temperature data, so that the weight coefficient is adjusted, and the denoising effect is improved. According to the distance between the temperature data in all the temperature time sequence data sequences and the abrupt change value of the temperature data, the isolated value of each temperature data is obtained, so that the weight coefficient of each temperature data is obtained, the reliability of the data in the local range is detected through the similarity analysis between a plurality of temperature time sequence data sequences, the accuracy of the jump degree is ensured, and the reliability of the weight coefficient is ensured. And performing weighted average filtering treatment to obtain an air conditioner start-stop instruction in the food processing material storage warehouse. The invention improves the denoising effect of the temperature time sequence data sequence through the weight coefficient of the self-adaptive temperature data, and obtains accurate and reliable temperature data, thereby obtaining accurate control instructions and improving the effect of controlling the food processing material pipe.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a method for controlling food processing materials according to 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 a food processing material management method and system according to the 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 a food processing material management and control method and system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for controlling food processing materials according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: in a food processing material storage warehouse, acquiring temperature data of different areas in the warehouse within a period of time to obtain a plurality of temperature time sequence data sequences; recording any one temperature time sequence data sequence as a target sequence; recording any one temperature data in the target sequence as main data; and obtaining the mutation value of the main data according to the difference between the main data and the adjacent data in the target sequence.
The purpose of this embodiment is to perform local range quantization analysis on the acquired data, so as to adaptively select the weight of each data when participating in mean filtering, and improve the noise filtering effect.
When the data is smoothed by mean filtering, the weights of all the data in the default filter window are the same. However, in the currently mentioned problem, there are both noise data in the fluctuating data points and variations in the temperature data itself. Therefore, it is necessary to distinguish the difference between the two fluctuations according to the local characteristics of the data, so that the weight of the data representing the noise fluctuation is reduced and the interference of the noise is reduced as much as possible when the weighted average filtering is performed subsequently.
In actual warehouse storage, because of a large storage area, multiple sensors are often used to monitor multiple local positions together. In the food storage environment, the temperature change is usually induced by the transient change of the temperature driven by the air flow fluctuation caused by the entrance and exit of personnel, and the temperature change caused by the day-night temperature difference of the external environment or the seasonal change and the like is caused by the insufficient heat insulation measures, and the changes usually exist in the whole storage environment, so that for the changes, all sensors in the current storage can be regarded as constant characteristics, the noise data mentioned above are random characteristics of a certain sensor, and therefore, the difference of fluctuation quantification characteristics of a single sensor can be further enlarged based on the characteristics, and the limitation that the fluctuation difference is not large enough is weakened.
In a food processing material storage warehouse, a plurality of temperature sensors are used for collecting temperature data of different areas in the warehouse within a period of time, so as to obtain a plurality of temperature time sequence data sequences.
What needs to be described is: in this embodiment, the sampling frequency of the temperature data is one time per minute, and this is described as an example, and other values may be set in other embodiments, and the embodiment is not limited thereto.
For environmental data such as temperature data, the maximum difference between the normal fluctuation data and the noise data is that the noise fluctuation is usually represented as a local feature of high-frequency persistence, while the fluctuation of the temperature data itself is changed, the change speed is usually small, and continuous fluctuation occurs less. Thus, according to the feature, a quantization analysis is required for the local feature where each data is located.
Therefore, the mutation value is obtained according to the difference of adjacent temperature data, and the jump degree is obtained according to the mutation value of all the data in the local range of the temperature data.
It is known that in a conventional environment, the change in temperature data is generally not too severe and frequent alternation of increasing and decreasing is less likely to occur, so that based on this feature, the abrupt values of all data are calculated first within a certain local range of temperature data.
And recording any one temperature time sequence data sequence as a target sequence. And recording any one temperature data in the target sequence as main data.
The calculation formula of the mutation value A of the main data is known as follows:
wherein A is the mutation value of the main data, B is the data value of the main data,for the data value of the preceding temperature data adjacent to the main data in the target sequence, +.>Is the data value of the next temperature data adjacent to the main data in the target sequence, and is an absolute value function. />Normalizing the data values to [0,1 ] as a linear normalization function]Within the interval.
What needs to be described is: when the three temperature data are in increments or decrements,should be equal to->When there is a data fluctuation in these three temperature data, +.>Should be greater thanTherefore, use->The larger A is the mutation value of the main data, namely the more important the main data, 1 is added to the numerator and denominator in the formula to prevent the denominator from being 0 and maintain the proportion of the numerator and the denominator.
According to the mode, the mutation value of each temperature data in each temperature time sequence data sequence is obtained.
What needs to be described is: in the target sequence, when the main data is the first or last temperature data, the previous or the next temperature data does not exist, so the embodiment makes the mutation value of the first temperature data equal to the mutation value of the second temperature data, and the mutation value of the last temperature data equal to the mutation value of the last but one temperature data, which is described as an example, and other embodiments can obtain the mutation values of the first and the last temperature data in the sequence by other ways, which are not limited in the embodiment.
Step S002: and in the target sequence, obtaining the jump degree of the main data according to the difference and the mutation value of the main data and the surrounding temperature data.
The preset number threshold L in this embodiment is 40, which is described as an example, and other values may be set in other embodiments, which is not limited in this embodiment.
In the target sequence, the main data, the sequence segment composed of L temperature data before the main data and L temperature data after the main data are recorded as the reference sequence segment corresponding to the main data. Each temperature data in the reference sequence segment is noted as reference data.
What needs to be described is: if the L temperature data are not satisfied before or after the main data, only the temperature data existing before or after the main data are analyzed later. And the reference data in the reference sequence segment is the local range in which the main data is located.
For the situation that whether noise interference exists in the local range of the main data, the most direct is the situation that the discrete difference of the data values of all the data in the local range is calculated, but the variance of the discrete difference is conventionally represented, only the difference in the numerical value of the data points in the local range is considered, and the situation that whether frequent increase and decrease alternate occurrence exists in the local range is not represented, so that when the variance is calculated, the mutation value of each data point obtained through calculation is combined and taken as a weight, and the data jump degree in the local range of the main data is obtained.
The calculation formula of the jump degree C of the main data is known as follows:
where C is the degree of jump of the main data, n is the number of reference data,for the data value of the ith reference data,for the mean value of the data values of all reference data, +.>Is the mutation value of the ith reference data.
What needs to be described is: the variance of the data values of all the reference data is calculated to represent the data value difference in the local range of the main data, and the mutation value of each reference data is taken as the weight of the data value difference, so that the reference data with larger mutation value contributes more in variance calculation. Thereby usingThe larger C represents the jump degree of the main data, which indicates that the temperature data in the local range has higher variation amplitude, and the stronger the internal features that the increase and the decrease alternately and continuously appear, the more the corresponding noise interference is likely to happen.
Step S003: the temperature time sequence data sequence which is not the target sequence is marked as a control sequence; obtaining a local similarity coefficient of main data when the target sequence is matched with each control sequence according to the distance between the target sequence and the temperature data in each control sequence and the mutation value of the temperature data; and obtaining the isolated value of the main data according to the local similarity coefficient of the main data when the target sequence is matched with all the comparison sequences.
However, when the noise data and the temperature data are superimposed by the fluctuation of the data, the fluctuation amplitude and the change speed are further different, so that the original high-frequency continuous characteristic of the noise and the normal fluctuation characteristic of the temperature data are weakened, namely, the difference represented by the quantitative analysis according to the local characteristic is not large enough. It is therefore necessary to further analyze the data differences between the temperature time series data sequences acquired by the plurality of temperature sensors.
Therefore, the similarity coefficient of the sensor in the same local range can be obtained according to the DTW algorithm, and the isolation value of the current sensor can be obtained.
The presence of a superposition of noise data and normal fluctuations in the local ranges may result in the calculated degree of jump being impaired, and therefore, for such cases, a factor of sensitivity is given to the degree of jump for each local range in combination with the difference in the simultaneous sequence of the remaining sensors, whereby the degree of jump is further supplemented in accordance with the represented outlier characteristics of each sensor.
And marking the ordinal value of the main data in the target sequence as a main ordinal value.
The temperature sequence data sequence which is not the target sequence is recorded as a control sequence. Any one of the control sequences was designated as the main control sequence.
In the main comparison sequence, the temperature data corresponding to the main ordinal value is recorded as comparison main data.
In the main control sequence, a sequence segment composed of control main data, L pieces of temperature data before the control main data and L pieces of temperature data after the control main data is recorded as a control sequence segment corresponding to the control main data. And L is a preset quantity threshold value.
And obtaining a distance value sequence corresponding to the reference sequence segment and the control sequence segment by using a DTW algorithm. Each distance value in the distance value sequence corresponds to one temperature data in the reference sequence segment and one temperature data in the control sequence segment.
What needs to be described is: the DTW algorithm is a well known technique, and specific methods are not described here. The algorithm calculates the optimal matching path of each point between two time sequences by a dynamic programming method, calculates the distance between the matching points, and finally can obtain a distance value sequence, wherein each distance value in the distance value sequence represents the distance between two time sequence data points at corresponding positions. The sum of all the distance values in the distance value sequence is the DTW distance of the two time sequences, and the smaller the DTW distance is, the more similar the two time sequences are.
Conventional DTW algorithms calculate similarity by calculating the minimum distance each data point corresponds to a data point in another sequence. The similarity is characterized by taking the accumulation of the minimum distance as the cost, but because the noise data and the normal fluctuation data have certain difference in the scene, when the noise is seriously interfered, the calculation of the similarity is also needed to be adjusted by combining the data scene aimed at by the embodiment. Therefore, the embodiment performs weighted summation on the data in the distance value sequence obtained by the DTW algorithm to obtain accurate similarity.
In the distance value sequence, the abrupt change value of one temperature data in the reference sequence segment corresponding to each distance value is recorded as the main abrupt change value of each distance value. And recording the mutation value of one temperature data in the control sequence segment corresponding to each distance value as a mutation value of each distance value.
From this, the calculation formula of the local similarity coefficient D of the main data when the target sequence matches the main control sequence is known as follows:
wherein D is a local similarity coefficient of the main data when the target sequence is matched with the main control sequence, m is the number of distance values in the distance value sequence,for the j-th distance value in the sequence of distance values, for example>Is the main mutation value of the j-th distance value in the distance value sequence, <>Is the mutation value of the j-th distance value in the distance value sequence.
What needs to be described is:the smaller the data change trend in the corresponding reference sequence segment and control sequence segment is, the more similar the data change trend is, the +.>And->The larger the pair->The greater the effect of acquisition, the more so when +>And->The greater the ∈ ->Smaller adjustment value->Due to->And->Are normalized values, thus use +.>Representation->Thereby reducing the influence of the data with larger mutation values on the distance between the reference sequence segment and the control sequence segment, i.e. eliminating the influence of noise on the similarity of the reference sequence segment and the control sequence segment, thus whenThe smaller the reference sequence section and the control sequence section are, the more similar the reference sequence section and the control sequence section are, so that according to the similar characteristics between the temperature time sequence data sequences acquired by the temperature sensors, the more reliable the data in the reference sequence section are, and therefore the use of +.>The partial similarity coefficient of the main data when the target sequence is matched with the main control sequence is represented, and the denominator is added with 1 in the formula to prevent the denominator from being 0, when D is larger, the more similar the reference sequence section and the control sequence section are, the more reliable the data in the reference sequence section are, so that the more reliable the jump degree C of the main data is.
According to the mode, the local similarity coefficient of the main data when the target sequence is matched with each control sequence is obtained.
Since there are a plurality of temperature sensors, it is necessary to further analyze the local similarity coefficient of the main data when the target sequence and all the control sequences match.
And (3) marking the average value of the local similarity coefficients of the main data when the target sequence is matched with all the control sequences as an isolated value of the main data.
What needs to be described is: the larger the isolated value, the more similar the data of the temperature time sequence data sequences acquired by all the temperature sensors in a certain time period is, so that the more reliable the data in the reference sequence segment in the time period in the target sequence is, namely the more reliable the C is.
Step S004: obtaining a weight coefficient of the main data according to the isolated value of the main data and the jump degree of the main data; and obtaining an air conditioner start-stop instruction in the food processing material storage warehouse according to the weight coefficients of all the temperature data in all the temperature time sequence data sequences.
The calculation formula of the weight coefficient P of the main data is known as follows:
where P is the weight coefficient of the main data,is the isolated value of the main data, C is the jump degree of the main data,normalizing the data values to [0,1 ] as a linear normalization function]Within the interval.
What needs to be described is: the larger C is, the greater the degree of noise interference received in the reference sequence segment corresponding to the main data isThe larger the data in the reference sequence segment corresponding to the main data is, the more trusted the data is, namely the more trusted the C is, so +.>The larger the description is, the more likely it is noise, thus using +.>The more likely the main data is noise, the smaller the weight coefficient is, so that the influence of noise is reduced, and the noise filtering effect is improved.
According to the mode, the weight coefficient of each temperature data in the target sequence is obtained.
And filtering and denoising the target sequence by using a weighted average filtering algorithm according to the weight coefficients of all the temperature data in the target sequence to obtain a denoising data sequence of the target sequence.
What needs to be described is: the weighted average filtering algorithm is a well known technique, and a specific method is not described here. The filter window length is a main parameter in the weighted average filter algorithm, and the preset filter window length in this embodiment is 5, which is described as an example, and other values may be set in other embodiments, which is not limited in this embodiment. Taking main data in a target sequence as an example, taking the main data as a filtering window center to obtain 5 temperature data in the filtering window, wherein the data value after denoising the main data isWherein->Weight coefficient for the xth temperature data in the filter window, < >>Weight coefficient sum of all temperature data in the filter window, +.>Is the data value of the xth temperature data within the filter window.
And obtaining the denoising data sequence of each temperature time sequence data sequence according to the mode.
And transmitting the denoising data sequences of all the temperature time sequence data sequences to a warehouse management system to obtain an air conditioner start-stop instruction in the food processing material storage warehouse. Therefore, the start and stop of the air conditioner in the warehouse are controlled, the influence on material storage caused by the change of the external temperature is avoided, and timely management and control of food processing materials are completed.
What needs to be described is: the warehouse management system is common warehouse temperature control software in the current market, can monitor parameters such as temperature, humidity and the like in a warehouse in real time, and provides an alarm function and remote control capability. The software also comprises data center monitoring software, a monitoring and data acquisition system, internet of things platform software and the like, and also has a temperature regulation function.
The present invention has been completed.
In summary, in the embodiment of the present invention, temperature data of different areas in a food processing material storage warehouse in a period of time is collected to obtain a plurality of temperature time series data sequences, and a sudden change value of each temperature data in the temperature time series data sequences is obtained, so as to obtain a jumping degree of each temperature data. According to the distance between the temperature data in all the temperature time sequence data sequences and the abrupt change value of the temperature data, the isolated value of each temperature data is obtained, so that the weight coefficient of each temperature data is obtained, and the weighted average filtering processing is carried out, so that the air conditioner start-stop instruction in the food processing material storage warehouse is obtained. According to the invention, the denoising effect of the temperature time sequence data sequence is improved through the weight coefficient of the self-adaptive temperature data, and accurate and reliable temperature data is obtained, so that an accurate control instruction is obtained, and the effect of controlling the food processing material pipe is improved.
The invention also provides a food processing material management and control system, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the food processing material management and control method.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of controlling food processing materials, the method comprising the steps of:
in a food processing material storage warehouse, acquiring temperature data of different areas in the warehouse within a period of time to obtain a plurality of temperature time sequence data sequences; recording any one temperature time sequence data sequence as a target sequence; recording any one temperature data in the target sequence as main data; obtaining a mutation value of the main data according to the difference between the main data and the adjacent data in the target sequence;
in the target sequence, according to the difference and mutation value of the main data and the surrounding temperature data, obtaining the jump degree of the main data;
the temperature time sequence data sequence which is not the target sequence is marked as a control sequence; obtaining a local similarity coefficient of main data when the target sequence is matched with each control sequence according to the distance between the target sequence and the temperature data in each control sequence and the mutation value of the temperature data; obtaining an isolated value of the main data according to the local similarity coefficient of the main data when the target sequence is matched with all the comparison sequences;
obtaining a weight coefficient of the main data according to the isolated value of the main data and the jump degree of the main data; and obtaining an air conditioner start-stop instruction in the food processing material storage warehouse according to the weight coefficients of all the temperature data in all the temperature time sequence data sequences.
2. The method for controlling food processing materials according to claim 1, wherein the specific calculation formula corresponding to the mutation value of the main data obtained according to the difference between the main data and the adjacent data in the target sequence is:
wherein A is the mutation value of the main data, B is the data value of the main data,for the data value of the preceding temperature data adjacent to the main data in the target sequence, +.>For the data value of the next temperature data adjacent to the main data in the target sequence, ||is an absolute function, |is +.>Is a linear normalization function.
3. The method for controlling food processing materials according to claim 1, wherein the step of obtaining the jump degree of the main data in the target sequence according to the difference and the mutation value of the main data and the surrounding temperature data comprises the following specific steps:
in the target sequence, the main data, a sequence segment formed by L temperature data before the main data and L temperature data after the main data are recorded as a reference sequence segment corresponding to the main data; the L is a preset quantity threshold value;
recording each temperature data in the reference sequence segment as reference data;
and obtaining the jump degree of the main data according to the data values and the mutation values of all the reference data.
4. The method for controlling food processing materials according to claim 3, wherein the specific calculation formula corresponding to the jump degree of the main data is obtained according to the data values and the abrupt change values of all the reference data:
where C is the degree of jump of the main data, n is the number of reference data,data value for the ith reference data, < +.>For the mean value of the data values of all reference data, +.>Is the mutation value of the ith reference data.
5. A method for controlling food processing materials according to claim 3, wherein the step of obtaining the local similarity coefficient of the main data when the target sequence matches each control sequence according to the distance between the target sequence and the temperature data in each control sequence and the mutation value of the temperature data comprises the following specific steps:
the ordinal value of the main data in the target sequence is marked as a main ordinal value;
marking any one control sequence as a main control sequence;
the temperature data corresponding to the main ordinal value in the main comparison sequence is marked as comparison main data;
in the main comparison sequence, a sequence segment formed by comparison main data, L temperature data before the comparison main data and L temperature data after the comparison main data is recorded as a comparison sequence segment corresponding to the comparison main data;
obtaining a distance value sequence corresponding to the reference sequence segment and the comparison sequence segment by using a DTW algorithm; each distance value in the distance value sequence corresponds to one temperature data in the reference sequence section and one temperature data in the comparison sequence section;
in the distance value sequence, recording a mutation value of one temperature data in a reference sequence section corresponding to each distance value as a main mutation value of each distance value; recording the mutation value of one temperature data in the control sequence section corresponding to each distance value as a mutation value of each distance value;
and obtaining the local similarity coefficient of the main data when the target sequence is matched with the main control sequence according to all the distance values in the distance value sequence, the main mutation values and the mutation values.
6. The method for controlling food processing materials according to claim 5, wherein the specific calculation formula corresponding to the local similarity coefficient of the main data when the target sequence is matched with the main control sequence is obtained according to all the distance values in the distance value sequence and the main mutation values and the mutation values thereof, wherein the specific calculation formula is as follows:
wherein D is a local similarity coefficient of the main data when the target sequence is matched with the main control sequence, m is the number of distance values in the distance value sequence,for the j-th distance value in the sequence of distance values, for example>Is the main mutation value of the j-th distance value in the distance value sequence, <>Is the mutation value of the j-th distance value in the distance value sequence.
7. The method of claim 1, wherein the step of obtaining the isolated value of the main data based on the local similarity coefficient of the main data when the target sequence matches all the control sequences comprises the steps of:
and (3) marking the average value of the local similarity coefficients of the main data when the target sequence is matched with all the control sequences as an isolated value of the main data.
8. The method for controlling food processing materials according to claim 1, wherein the step of obtaining the weight coefficient of the main data according to the isolated value of the main data and the jump degree of the main data comprises the following specific steps:
calculating the product of the isolated value and the jump degree of the main data, calculating the normalized value of the product, and recording one minus the normalized value as the weight coefficient of the main data.
9. The method for controlling food processing materials according to claim 1, wherein the step of obtaining the air conditioner start-stop instruction in the food processing material storage warehouse according to the weight coefficients of all the temperature data in all the temperature time sequence data comprises the following specific steps:
according to the weight coefficients of all temperature data in the target sequence, filtering and denoising the target sequence by using a weighted average filtering algorithm to obtain a denoising data sequence of the target sequence;
and transmitting the denoising data sequences of all the temperature time sequence data sequences to a warehouse management system to obtain an air conditioner start-stop instruction in the food processing material storage warehouse.
10. A food processing material management system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor performs the steps of a food processing material management method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713472.7A CN117408497B (en) | 2023-12-14 | 2023-12-14 | Food processing material management and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713472.7A CN117408497B (en) | 2023-12-14 | 2023-12-14 | Food processing material management and control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117408497A true CN117408497A (en) | 2024-01-16 |
| CN117408497B CN117408497B (en) | 2024-04-05 |
Family
ID=89500284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311713472.7A Active CN117408497B (en) | 2023-12-14 | 2023-12-14 | Food processing material management and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117408497B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668468A (en) * | 2024-01-31 | 2024-03-08 | 山东省舜天化工集团有限公司 | Intelligent analysis management system for chemical preparation data |
| CN118037134A (en) * | 2024-04-11 | 2024-05-14 | 山东东阿润康阿胶制品有限公司 | Characteristic information extraction method and system for donkey-hide gelatin cake production process |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19647158A1 (en) * | 1996-11-14 | 1998-05-20 | Siemens Ag | Temperature path regulation method for industrial oven for curing of plastics |
| CN104090608A (en) * | 2014-06-16 | 2014-10-08 | 华中科技大学 | Phytotron control method |
| US20150045691A1 (en) * | 2013-03-01 | 2015-02-12 | Huazhong University Of Science And Technology | Method and system for in-vivo temperature measurement based on ac magnetization of magnetic nanoparticle |
| CN105303536A (en) * | 2015-11-26 | 2016-02-03 | 南京工程学院 | Median filtering algorithm based on weighted mean filtering |
| CN106161877A (en) * | 2016-08-01 | 2016-11-23 | 深圳市瀚晖威视科技有限公司 | A kind of image frame noise-reduction method for starlight level video camera |
| WO2021129448A1 (en) * | 2019-12-24 | 2021-07-01 | 追觅科技(上海)有限公司 | Sudden temperature change detection method and device, and storage medium |
| CN117167903A (en) * | 2023-11-03 | 2023-12-05 | 江苏中安建设集团有限公司 | Artificial intelligence-based foreign matter fault detection method for heating ventilation equipment |
-
2023
- 2023-12-14 CN CN202311713472.7A patent/CN117408497B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19647158A1 (en) * | 1996-11-14 | 1998-05-20 | Siemens Ag | Temperature path regulation method for industrial oven for curing of plastics |
| US20150045691A1 (en) * | 2013-03-01 | 2015-02-12 | Huazhong University Of Science And Technology | Method and system for in-vivo temperature measurement based on ac magnetization of magnetic nanoparticle |
| CN104090608A (en) * | 2014-06-16 | 2014-10-08 | 华中科技大学 | Phytotron control method |
| CN105303536A (en) * | 2015-11-26 | 2016-02-03 | 南京工程学院 | Median filtering algorithm based on weighted mean filtering |
| CN106161877A (en) * | 2016-08-01 | 2016-11-23 | 深圳市瀚晖威视科技有限公司 | A kind of image frame noise-reduction method for starlight level video camera |
| WO2021129448A1 (en) * | 2019-12-24 | 2021-07-01 | 追觅科技(上海)有限公司 | Sudden temperature change detection method and device, and storage medium |
| CN117167903A (en) * | 2023-11-03 | 2023-12-05 | 江苏中安建设集团有限公司 | Artificial intelligence-based foreign matter fault detection method for heating ventilation equipment |
Non-Patent Citations (1)
| Title |
|---|
| 葛馨远;孙中伟;许刚;: "基于小波域隐Markov树模型及重要性修正的绝缘子红外图像去噪研究", 电网技术, no. 2, 31 December 2007 (2007-12-31), pages 91 - 97 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668468A (en) * | 2024-01-31 | 2024-03-08 | 山东省舜天化工集团有限公司 | Intelligent analysis management system for chemical preparation data |
| CN117668468B (en) * | 2024-01-31 | 2024-04-26 | 山东省舜天化工集团有限公司 | Intelligent analysis management system for chemical preparation data |
| CN118037134A (en) * | 2024-04-11 | 2024-05-14 | 山东东阿润康阿胶制品有限公司 | Characteristic information extraction method and system for donkey-hide gelatin cake production process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117408497B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117408497B (en) | Food processing material management and control method and system | |
| CN112817354A (en) | Livestock and poultry house culture environment temperature prediction control system and regulation and control method thereof | |
| CN115600932A (en) | Cultural relic storage environment abnormity assessment method based on big data | |
| CN112451834B (en) | Sleep quality management method, device, system and storage medium | |
| CN116592951A (en) | Intelligent cable data acquisition method and system | |
| CN116320042A (en) | Internet of things terminal monitoring control system for edge calculation | |
| CN117708748B (en) | Operation monitoring system and method for centrifugal fan | |
| CN117436353B (en) | Intelligent recreation facility fault prediction method based on big data | |
| CN116400870A (en) | On-site construction on-line management system based on Internet of things | |
| CN117114213B (en) | Rural network co-construction convenience network service method and system | |
| CN113883672B (en) | Noise type identification method, air conditioner and computer readable storage medium | |
| CN117349664B (en) | On-line monitoring method and system for sprouting vegetable growth environment | |
| CN111145895A (en) | Abnormal data detection method and terminal equipment | |
| CN116991841A (en) | Data intelligent cleaning method for mixed wind data model | |
| CN110973687B (en) | Accurate control method for moisture in silk making process | |
| CN117311417A (en) | Intelligent agricultural information comprehensive management method and system based on Internet of things | |
| CN112432316B (en) | Air conditioner control method and device, electronic equipment and storage medium | |
| CN118010939B (en) | Intelligent formaldehyde detection method | |
| CN116389183B (en) | Intelligent home interaction data processing method based on Internet of things | |
| CN117421538B (en) | Detail waterproof data regulation and optimization method | |
| CN117739405A (en) | Heat supply control method and system based on intelligent regulating valve | |
| CN117874445B (en) | Enzyme preparation production monitoring method for real-time online monitoring data analysis | |
| CN117804639B (en) | Temperature calibration method and system for temperature control sensor of cementing machine | |
| CN117556386B (en) | Temperature data monitoring method in furnace refining process | |
| CN118091325B (en) | Intelligent cable detection method and system |
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 |