CN117130265B - Self-adaptive control method and system for health product transportation environment - Google Patents
Self-adaptive control method and system for health product transportation environment Download PDFInfo
- Publication number
- CN117130265B CN117130265B CN202311402712.1A CN202311402712A CN117130265B CN 117130265 B CN117130265 B CN 117130265B CN 202311402712 A CN202311402712 A CN 202311402712A CN 117130265 B CN117130265 B CN 117130265B
- Authority
- CN
- China
- Prior art keywords
- index
- variation
- matrix
- adaptive
- self
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000036541 health Effects 0.000 title claims abstract description 53
- 239000011159 matrix material Substances 0.000 claims abstract description 107
- 230000008569 process Effects 0.000 claims abstract description 25
- 230000003044 adaptive effect Effects 0.000 claims description 40
- 230000002159 abnormal effect Effects 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000006978 adaptation Effects 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 9
- 230000000694 effects Effects 0.000 description 11
- 230000001276 controlling effect Effects 0.000 description 9
- 239000006096 absorbing agent Substances 0.000 description 8
- 230000035939 shock Effects 0.000 description 8
- 230000001186 cumulative effect Effects 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000005315 distribution function Methods 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004378 air conditioning Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013173 literature analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a self-adaptive control method and a self-adaptive control system for a health product transportation environment, which relate to the technical field of self-adaptive control and comprise the following steps: the method comprises the steps of obtaining transportation influence indexes for transporting health-care products, including carriage temperature, carriage humidity, sunlight intensity and vehicle amplitude, establishing an index matrix, outputting a real-time index matrix, collecting a historical sample data set, generating probability density functions corresponding to all indexes respectively, calculating index variation probability, generating a variation index matrix, carrying out self-adaptive evolution identification, outputting a self-adaptive control result, including optimized control parameters of all indexes, and inputting the optimized control parameters into a carriage control module to control vehicles for transporting the health-care products. The invention solves the technical problems that the prior art cannot effectively process the influence of a plurality of influencing factors on the transportation of health care products, and the self-adaptive parameter control is lacking, so that the environmental stability in the transportation process is poor.
Description
Technical Field
The invention relates to the technical field of self-adaptive control, in particular to a self-adaptive control method and a self-adaptive control system for a health-care product transportation environment.
Background
During transportation, the environmental conditions of the health care product may be changed abnormally, such as at too high a temperature, at too low a humidity, etc., and if the abnormal changes cannot be found and handled in time, the abnormal changes will have a negative effect on the quality and effect of the health care product. In addition, the transportation environment of the health care product needs to consider a plurality of influencing factors, such as carriage temperature, humidity, sunlight intensity, vehicle amplitude and the like, and the influencing factors can directly influence the quality and effect of the health care product in the transportation process. The traditional environment control method often cannot comprehensively consider the change conditions under a plurality of influence factors, and is lack of self-adaptive parameter control, so that the environment control effect is not ideal, and the quality and the safety of the health care product are further influenced.
Therefore, a certain lifting space exists for the control of the transportation environment of the health products.
Disclosure of Invention
The application aims to solve the technical problems that the prior art lacks comprehensive environmental indexes in the transportation process of the health products, cannot effectively treat the influence of a plurality of influencing factors on the transportation of the health products, lacks adaptive parameter control and causes poor environmental stability in the transportation process by providing the self-adaptive control method and the self-adaptive control system for the transportation environment of the health products.
In view of the above problems, the present application provides a method and a system for adaptively controlling a health product transportation environment.
In a first aspect of the disclosure, a method for adaptively controlling a health product transportation environment is provided, where the method includes: acquiring transportation influence indexes for transporting health-care products, wherein the transportation influence indexes at least comprise carriage temperature, carriage humidity, sunlight intensity and vehicle amplitude; establishing an index matrix by using the transportation influence index, collecting real-time index data, filling the index matrix, and outputting the real-time index matrix; transporting sample data sets corresponding to all indexes through collection histories, analyzing the sample data sets, and generating probability density functions corresponding to all the indexes respectively, wherein the probability density functions are used for defining abnormal change probabilities of the corresponding indexes; performing index variation probability calculation on the real-time index matrix by using the probability density function to generate a variation index matrix, wherein each index in the variation index matrix corresponds to one variation probability; performing self-adaptive evolution recognition on the variation index matrix, and outputting a self-adaptive control result, wherein the self-adaptive control result comprises optimized control parameters of all indexes; and the carriage control module is connected, and the self-adaptive control result is input into the carriage control module to control the vehicle for transporting the health care products.
In another aspect of the disclosure, there is provided a system for adaptively controlling a health care product transportation environment, the system being used in the above method, the system comprising: an influence index acquisition unit for acquiring a transportation influence index for transporting the health product, wherein the transportation influence index at least comprises a compartment temperature, a compartment humidity, a sunlight intensity and a vehicle amplitude; the index matrix establishing unit is used for establishing an index matrix by using the transportation influence index, acquiring real-time index data, filling the index matrix and outputting a real-time index matrix; the sample data analysis unit is used for transporting sample data sets corresponding to the indexes through collection histories, analyzing the sample data sets and generating probability density functions corresponding to the indexes respectively, wherein the probability density functions are used for defining abnormal change probabilities of the corresponding indexes; the variation probability calculation unit is used for calculating the index variation probability of the real-time index matrix by utilizing the probability density function to generate a variation index matrix, wherein each index in the variation index matrix corresponds to one variation probability; the control result output unit is used for carrying out self-adaptive evolution identification on the variation index matrix and outputting a self-adaptive control result, wherein the self-adaptive control result comprises optimized control parameters of each index; and the vehicle control unit is used for being connected with the carriage control module, inputting the self-adaptive control result into the carriage control module and controlling the vehicle for transporting the health care products.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the environment condition of the health care product in the transportation process can be comprehensively monitored through comprehensive monitoring of a plurality of indexes such as the temperature of the carriage, the humidity of the carriage, the sunlight intensity and the vehicle amplitude, so that the change condition of the transportation environment of the health care product is timely perceived, and the environmental stability in the transportation process is ensured; the historical data set is utilized for analysis, and a probability density function related to each index is generated, so that the abnormal change probability of the corresponding index is defined, whether the abnormal change exists in each index can be more accurately judged, and the sensitivity and the accuracy to the transportation environment problem are improved; the method and the device have the advantages that the index variation probability of the real-time index matrix is calculated, and the control parameters are optimized through self-adaptive evolution recognition, so that the self-adaptive adjustment of the health-care product transportation environment is realized, and the transportation success rate and the quality guarantee of the health-care products are improved. In summary, the self-adaptive control method for the health care product transportation environment solves the technical problems of comprehensive consideration, real-time requirement, control parameter adjustment and the like in the prior art, and can more accurately judge abnormal change and control requirement through comprehensive analysis of influence indexes and application of probability density functions, thereby realizing self-adaptive control on the health care product transportation vehicle and improving safety and stability of the transportation process.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a method for adaptively controlling a transportation environment of a health product according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a self-adaptive control system for a health care product transportation environment according to an embodiment of the present application.
Reference numerals illustrate: an influence index acquisition unit 10, an index matrix creation unit 20, a sample data analysis unit 30, a variation probability calculation unit 40, a control result output unit 50, and a vehicle control unit 60.
Detailed Description
According to the self-adaptive control method for the health-care product transportation environment, the technical problems that the prior art lacks comprehensive environmental indexes in the health-care product transportation process, cannot effectively treat the influence of a plurality of influence factors on the health-care product transportation, lacks self-adaptive parameter control and is poor in environmental stability in the transportation process are solved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for adaptively controlling a health product transportation environment, where the method includes:
acquiring transportation influence indexes for transporting health-care products, wherein the transportation influence indexes at least comprise carriage temperature, carriage humidity, sunlight intensity and vehicle amplitude;
firstly, the goal of transporting health products is to ensure that the health products are in proper environmental conditions during transportation to maintain their quality and effect, and according to requirements, transportation impact indicators for transporting health products are obtained, including cabin temperature, cabin humidity, solar intensity and vehicle amplitude, and the values of these indicators can be monitored and recorded by means of sensor devices.
Establishing an index matrix by using the transportation influence index, collecting real-time index data, filling the index matrix, and outputting the real-time index matrix;
according to the acquired transport impact index, an index matrix is established, wherein each row represents a time point, and each column represents a transport impact index. Real-time data of the transport impact indicators are collected at predetermined time intervals or trigger conditions using sensor devices such as temperature sensors, humidity sensors, light sensors, and vibration sensors, for example, recording data once per minute or when a specific event occurs.
And filling the acquired real-time index data into corresponding positions in the index matrix, ensuring that the corresponding relation between the data and the time point and the index is correct, and taking the whole index matrix as output after the filling of the real-time index data is completed, so that the real-time index matrix can provide the latest and comprehensive transportation influence index data for the subsequent steps.
Transporting sample data sets corresponding to all indexes through collection histories, analyzing the sample data sets, and generating probability density functions corresponding to all the indexes respectively, wherein the probability density functions are used for defining abnormal change probabilities of the corresponding indexes;
sample data sets corresponding to all indexes in the historical transportation process are collected, the sample data are index numerical data recorded and collected in the previous transportation process, statistical analysis is carried out on the sample data of each index to obtain the frequency distribution condition of the index, the change rule of the index is described by using a probability density function based on the frequency distribution, and the probability density function is used for defining the abnormal change probability of each index and providing basis for subsequent control and monitoring.
Further, the sample data set is analyzed to generate probability density functions corresponding to the indexes respectively, and the method further comprises:
acquiring attribute information of a health product to be transported, and acquiring a preset influence index according to the attribute information of the health product;
analyzing the sample data set by using the preset influence index, and taking the preset influence index as an abnormal change identification value to obtain a first distribution interval and a second distribution interval, wherein the first distribution interval is an interval smaller than the preset influence index, and the second distribution interval is an interval greater than or equal to the preset influence index;
and identifying the distribution of the sample data sets at the two ends of the preset influence index according to the first distribution interval and the second distribution interval, and defining a probability density function of the corresponding index according to the probability that the sample data set corresponding to each index is located in the second distribution interval.
And acquiring attribute information, including components, characteristics, sensitivity, stability and the like, of the health-care products to be transported, analyzing transportation influence indexes influencing the quality and effect of the health-care products according to the attribute information by expert experience, literature analysis and other methods, and acquiring preset influence indexes, wherein the preset influence indexes represent allowable critical values of the transportation influence indexes, namely, abnormality can exist if the transportation influence indexes exceed the allowable critical values.
For the obtained preset influence index, selecting one index as a value for identifying abnormal change, analyzing the sample data set by using the selected preset influence index as a reference, and particularly dividing the sample data set into two sections according to the size of the preset influence index, namely a first distribution section and a second distribution section, wherein the first distribution section comprises sample data smaller than the preset influence index value, and the second distribution section comprises sample data larger than or equal to the preset influence index value.
And according to the dividing mode, sample data belonging to the first distribution interval and the second distribution interval are screened from the sample data sets, so that two new data sets are respectively formed. And obtaining a first distribution interval and a second distribution interval corresponding to each index by analyzing the distribution condition of the sample data concentrated at the two ends of the preset influence index.
And calculating the probability of the sample data set in the second distribution interval aiming at each index, and dividing the number of samples in the second distribution interval by the total number of samples in the statistical sample data to obtain the probability of the index in the second distribution interval, wherein the probability represents the possibility of abnormal change trend of the index. The probability that the obtained index is in the second distribution interval is used as the basis of a probability density function of the defined index, and the probability density function is obtained by utilizing historical sample training, wherein the probability density function is used for describing the variation situation and the abnormal change probability of each index, and the defined probability density function is used for judging the abnormal situation of the index data in the follow-up self-adaptive control and carrying out proper adjustment and control.
The probability density function is expressed as follows:
；
wherein,to express that the ith index obeys the probability density function of normal distribution in the second distribution interval, ++>Adaptive weight corresponding to the ith index, < ->Is a sample data set with the ith index continuously changed, and，/>is the data of the preset influence index.
The probability density functionIs obtained by means of sample training,in order to represent that the ith index is in the probability density function of the second distribution interval obeying normal distribution, namely the probability distribution function of the index which is larger than or equal to a preset influence index, the probability distribution condition of the index in an abnormal transportation range is described.
The adaptive weight corresponding to the ith index is used for adjusting the sensitivity degree of the index to abnormal changes, the adaptive weight reflects the importance of the index in the transportation process and the degree of the index to be controlled, and the larger adaptive weight means that the variation of the index is more sensitive and is more concerned in the control process.
A sample data set indicating continuous variation of the ith index is an observation and record of continuous variation of the index in the historical transportation data, and each data point in the sample data set represents an actual index value at a time point. />The threshold value is used to determine whether the index value exceeds the normal range.
Performing index variation probability calculation on the real-time index matrix by using the probability density function to generate a variation index matrix, wherein each index in the variation index matrix corresponds to one variation probability;
for each index value in the real-time index matrix, calculating the variation probability of the index value by using a probability density function of the corresponding index, wherein the probability density function can describe the distribution condition of the index value, so that the abnormality degree of the current index value relative to the historical data can be determined, and according to the calculated variation probability, a corresponding variation probability is allocated to each index value in the real-time index matrix, and the variation probability is a value between 0 and 1 and represents the abnormality degree of the index value, so that each index in the variation index matrix has a corresponding variation probability. And replacing each index value in the original real-time index matrix with a corresponding variation probability value to form a new variation index matrix, wherein each index value in the variation index matrix represents the variation probability of the corresponding index and is used for representing the degree of abnormality of the index value.
Further, performing index variation probability calculation on the real-time index matrix by using the probability density function to generate a variation index matrix, including:
inputting the data of each index in the real-time index matrix into the probability density function, and generating a first interval by using the data of each index in the real-time index matrix and the preset influence index;
acquiring the integral of each index in the first interval and outputting an integral set;
and marking the variation probability of each index by using the integral set, outputting a variation probability set, and generating a variation index matrix according to the variation probability set.
The method comprises the steps of inputting data of each index into the probability density function in sequence aiming at the indexes in the real-time index matrix, and calculating according to the data of each index in the real-time index matrix and a preset influence index in the probability density function to obtain corresponding probability density values, wherein the probability density values represent positions of current index data on a probability distribution curve and reflect the probability of the current index data in an abnormal range. And combining the probability density values of each index into a section as a first section, wherein the first section represents the probability that each index data in the real-time index matrix is positioned in an abnormal range.
For each index, calculating a cumulative distribution function of the index in the first interval according to a probability density function of the first interval, wherein the cumulative distribution function represents the cumulative probability when the probability distribution curve of the index is larger than a preset influence index, and carrying out numerical integration calculation on the cumulative distribution function of each index to obtain an integral value of the index in the first interval, wherein the integral value reflects the probability of the index in an abnormal range. And recording the integral value of each index in the first interval to form an integral set, wherein the integral set comprises the integral result of each index in the first interval.
For each index, find the corresponding integral value in the integral set, normalize the integral value to make it inThe integrated value after normalization is used as variation probability to represent the probability of variation of the corresponding index, and a variation probability set is output, wherein the variation probability set comprises variation probability values of the indexes. And according to the data of the real-time index matrix and the corresponding variation probability in the variation probability set, distributing a variation probability value corresponding to each index in the variation index matrix to generate a variation index matrix, wherein the variation index matrix and the real-time index matrix have the same structure.
Performing self-adaptive evolution recognition on the variation index matrix, and outputting a self-adaptive control result, wherein the self-adaptive control result comprises optimized control parameters of all indexes;
and optimizing the data of each index by using the variation probability of each data in the variation index matrix as the basis of adaptability evaluation in an iterative mode, and determining a first index to be optimized according to the descending rate of each index of the current iteration round in each iteration, wherein the descending rate can be measured by using the variation probability.
After determining the first index, taking the first index as a starting point, and increasing the scaling step length of the index in the next iteration, wherein other indexes with higher association degree are required to be considered, and determining other indexes associated with the first index by judging the association degree of each index in the index matrix. In the next iteration, in addition to increasing the zoom step length of the first index, the zoom step length of other indexes related to the first index needs to be increased, so that the change trend of the related index and the first index is consistent. The iterative steps above are repeated until an adaptation objective is met, the adaptation objective being an optimization requirement that minimizes the probability of variation. When the adaptive target is satisfied, an adaptive control result is output, the adaptive control result including control parameters optimized for each index, the control parameters being used to adjust the transportation environment to keep the index varying within a suitable range.
Further, the adaptive evolution recognition is performed on the variation index matrix, and an adaptive control result is output, and the method further comprises:
taking the minimum variation probability of each data in the variation index matrix as an adaptation target, iterating the data of each index, and outputting a self-adaptive control result;
determining a first index according to the descending rate of each index of the current iteration round in the iteration process, increasing the zooming step length of the first index when the current iteration round is positioned at the next iteration round, and the like until the adaptation target is met, and outputting an adapted index matrix;
and inputting the adaptive control result into the carriage control module for control according to the adaptive index matrix.
Setting an initial scaling step value and an iteration counter, obtaining the variation probability of each index in the current iteration round by using the data in the variation probability set obtained by previous calculation, selecting the index with the largest variation probability in the current iteration round as a first index, increasing the scaling step of the first index by a certain proportion, for example doubling, checking whether the updated index matrix meets the adaptation target, namely minimizing the variation probability, and ending the iteration if the updated index matrix meets the adaptation target; otherwise, the next iteration is continued.
In the iteration process, the data of each index is iterated by utilizing an adaptive scaling factor, the size of the adaptive scaling factor is reduced along with the increase of iteration times, and the adaptive scaling factor expression is as follows:
；
wherein,for the scaling step of the next iteration round, t is the current iteration round, +.>Is->Maximum scaling step of iteration round, +.>Is->Minimum scaling step of iteration round, +.>Is the number of iterations that have been performed.
In each iteration process, t represents the current iteration round, and the value of t is gradually increased from the first iteration; t represents the total number of iterations, including the cumulative number of all iteration runs, and the value of T is incremented each time a complete iteration is performed. By using two variables, T and T, the scaling step can be dynamically adjusted according to the progress and number of iterations to achieve a better adaptive control effect.
From this expression, it can be seen that as the number of iterations increases, the adaptive scaling factorThe step length of the index data is gradually reduced when each iteration is performed, the step length of the index data is gradually reduced, the subsequent iteration process can be finer and more stable through the design, the data of each index can be better adjusted and optimized, and the step length is continuously reduced, so that the gradual approximation of an optimal solution is facilitated, and the self-adaptive control effect is improved.
And when the adaptation target is met, the index matrix obtained after the last round of iteration is used as the index matrix after adaptation to be output.
The adapted index matrix is used as input to represent the index state after the self-adaptive control of the transport vehicle, and is input into the carriage control module, and the carriage control module can implement corresponding control operation according to the change condition and the value of the indexes, so that the carriage control module can provide corresponding control strategy and decision according to the adapted index matrix to ensure the safety and the efficiency in the transport process, and simultaneously, the abnormal or variant indexes are properly adjusted and corrected.
Further, in the iterative process, determining a first index at a decreasing rate of each index of the current iteration round, and increasing a scaling step length of the first index when the current iteration round is located at the next iteration round, wherein the method further comprises:
judging the association degree of each index in the index matrix, and acquiring the association index of the first index after determining the first index according to the association degree of each index, wherein the association degree of the association index is larger than a preset association degree;
and increasing the scaling step length of the associated index while increasing the scaling step length of the first index in the next iteration round.
And calculating the association degree between each index in the index matrix by using a statistical method, such as a correlation coefficient method, so as to measure the linear relation degree between the indexes. According to specific requirements, a threshold value of a preset association degree is set, which indicates which other indexes with higher association degree with the first index are to be selected in the iterative process. And comparing the correlation degree between each index and the first index with a preset correlation degree threshold value, if the correlation degree is larger than the preset correlation degree threshold value, determining the first index as one correlation index, and taking all indexes meeting the correlation degree larger than the preset correlation degree threshold value as the correlation indexes of the first index, wherein the correlation indexes represent other indexes with higher correlation degree with the first index.
Determining the current iteration round, assuming the current iteration round is the q-th iteration round, and increasing the scaling step length of the first index in the next iteration round, namely the q+1th iteration round, so that the first index is greatly changed in the next iteration round; meanwhile, traversing the associated index set, and for each associated index, increasing the scaling step length of the associated index set in the next iteration round, wherein the change amplitude of the associated index set can be larger than that of other indexes by increasing the scaling step length. And using the first index and the associated index which are increased by the zooming step length, and correspondingly adjusting and optimizing in the next iteration. In this way, in the next iteration, the first index and the associated index have larger variation amplitude, so that the requirement of the self-adaptive control is better adapted, and the effect of the self-adaptive control is improved.
And the carriage control module is connected, and the self-adaptive control result is input into the carriage control module to control the vehicle for transporting the health care products.
Establishing a connection channel between an adaptive control system and a carriage control module in a network connection mode, transmitting an adaptive control result to the carriage control module, precisely controlling a vehicle for transporting health products according to optimized control parameters in the adaptive control result by the carriage control module, wherein the vehicle comprises environment parameters such as temperature, humidity, sunlight intensity and the like of the carriage, specifically, the temperature is regulated through an air conditioning system or a heater, the humidity is regulated through a humidifier or a dehumidifier, the air conditioning system or the heater, the humidifier or the dehumidifier comprise a plurality of air conditioning systems or the heater, the humidifier or the dehumidifier are uniformly distributed in the carriage, the light penetration degree is regulated through curtains, the curtains are covered on each window, and when an instruction of the carriage control module is received, the device is controlled according to the optimized control parameters of each index in the adaptive control result, so as to regulate the transportation environment, and keep the index to change in a proper range;
and reduce vibrations etc. through control vehicle amplitude, through setting up adjustable shock absorber at the carriage bottom plate, and adjustable shock absorber includes four adjustable shock absorbers at least, at carriage bottom plate evenly distributed setting, every adjustable shock absorber has the clearance adjustment ware, and the integration becomes adjustable shock absorber module, adjustable shock absorber module is connected with carriage control module, when the instruction from carriage control module is received to adjustable shock absorber module, the clearance adjustment of clearance adjustment ware realization and frame in each adjustable shock absorber, the displacement that effectively control vehicle carriage produced in the course of traveling plays the spacing function of fastening. Therefore, in the transportation process, each influence index can be reasonably regulated and controlled, so that the optimal transportation environment of the health-care products is provided, and the quality and the safety of the products are ensured.
In summary, the method and the system for adaptively controlling the transportation environment of the health product provided by the embodiment of the application have the following technical effects:
1. the environment condition of the health care product in the transportation process can be comprehensively monitored through comprehensive monitoring of a plurality of indexes such as the temperature of the carriage, the humidity of the carriage, the sunlight intensity and the vehicle amplitude, so that the change condition of the transportation environment of the health care product is timely perceived, and the environmental stability in the transportation process is ensured;
2. the historical data set is utilized for analysis, and a probability density function related to each index is generated, so that the abnormal change probability of the corresponding index is defined, whether the abnormal change exists in each index can be more accurately judged, and the sensitivity and the accuracy to the transportation environment problem are improved;
3. the method and the device have the advantages that the index variation probability of the real-time index matrix is calculated, and the control parameters are optimized through self-adaptive evolution recognition, so that the self-adaptive adjustment of the health-care product transportation environment is realized, and the transportation success rate and the quality guarantee of the health-care products are improved.
In summary, the self-adaptive control method for the health care product transportation environment solves the technical problems of comprehensive consideration, real-time requirement, control parameter adjustment and the like in the prior art, and can more accurately judge abnormal change and control requirement through comprehensive analysis of influence indexes and application of probability density functions, thereby realizing self-adaptive control on the health care product transportation vehicle and improving safety and stability of the transportation process.
Example two
Based on the same inventive concept as the adaptive control method for the health care product transportation environment in the foregoing embodiment, as shown in fig. 2, the present application provides an adaptive control system for the health care product transportation environment, where the system includes:
an influence index acquisition unit 10, wherein the influence index acquisition unit 10 is used for acquiring a transportation influence index for transporting the health care product, and the transportation influence index at least comprises a compartment temperature, a compartment humidity, a sunlight intensity and a vehicle amplitude;
an index matrix establishing unit 20, where the index matrix establishing unit 20 is configured to establish an index matrix with the transportation impact index, collect real-time index data, fill the index matrix, and output a real-time index matrix;
the sample data analysis unit 30 is configured to transport a sample data set corresponding to each index through the collection history, analyze the sample data set, and generate probability density functions corresponding to each index, where the probability density functions are used to define abnormal change probabilities of the corresponding indexes;
a variation probability calculation unit 40, where the variation probability calculation unit 40 is configured to perform index variation probability calculation on the real-time index matrix by using the probability density function, so as to generate a variation index matrix, where each index in the variation index matrix corresponds to a variation probability;
the control result output unit 50 is configured to perform adaptive evolution identification on the variation index matrix, and output an adaptive control result, where the adaptive control result includes optimized control parameters of each index;
and the vehicle control unit 60 is used for connecting with a carriage control module, and inputting the self-adaptive control result into the carriage control module to control the vehicle for transporting the health care products.
Further, the system also comprises a probability density function acquisition module for executing the following operation steps:
acquiring attribute information of a health product to be transported, and acquiring a preset influence index according to the attribute information of the health product;
analyzing the sample data set by using the preset influence index, and taking the preset influence index as an abnormal change identification value to obtain a first distribution interval and a second distribution interval, wherein the first distribution interval is an interval smaller than the preset influence index, and the second distribution interval is an interval greater than or equal to the preset influence index;
and identifying the distribution of the sample data sets at the two ends of the preset influence index according to the first distribution interval and the second distribution interval, and defining a probability density function of the corresponding index according to the probability that the sample data set corresponding to each index is located in the second distribution interval.
Further, the probability density function is expressed as follows:
；
wherein,to express that the ith index obeys the probability density function of normal distribution in the second distribution interval, ++>Adaptive weight corresponding to the ith index, < ->Is a sample data set with the ith index continuously changed, and，/>is the data of the preset influence index.
Further, the system further comprises a mutation index matrix generation module for executing the following operation steps:
inputting the data of each index in the real-time index matrix into the probability density function, and generating a first interval by using the data of each index in the real-time index matrix and the preset influence index;
acquiring the integral of each index in the first interval and outputting an integral set;
and marking the variation probability of each index by using the integral set, outputting a variation probability set, and generating a variation index matrix according to the variation probability set.
Further, the system further comprises an adaptive control result acquisition module, so as to execute the following operation steps:
taking the minimum variation probability of each data in the variation index matrix as an adaptation target, iterating the data of each index, and outputting a self-adaptive control result;
determining a first index according to the descending rate of each index of the current iteration round in the iteration process, increasing the zooming step length of the first index when the current iteration round is positioned at the next iteration round, and the like until the adaptation target is met, and outputting an adapted index matrix;
and inputting the adaptive control result into the carriage control module for control according to the adaptive index matrix.
Further, the data of each index is iterated by using an adaptive scaling factor, the size of which decreases with the increase of the iteration number, and the adaptive scaling factor expression is as follows:
；
wherein,for the scaling step of the next iteration round, t is the current iteration round, +.>Is->Maximum scaling step of iteration round, +.>Is->Minimum scaling step of iteration round, +.>Is the number of iterations that have been performed.
Further, the system also includes a zoom step adjustment module to perform the following operation steps:
judging the association degree of each index in the index matrix, and acquiring the association index of the first index after determining the first index according to the association degree of each index, wherein the association degree of the association index is larger than a preset association degree;
and increasing the scaling step length of the associated index while increasing the scaling step length of the first index in the next iteration round.
The foregoing detailed description of a method for adaptively controlling a health care product transportation environment will be clear to those skilled in the art, and the description of the apparatus disclosed in this embodiment is relatively simple, and the relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. The self-adaptive control method for the health product transportation environment is characterized by comprising the following steps of:
acquiring transportation influence indexes for transporting health-care products, wherein the transportation influence indexes at least comprise carriage temperature, carriage humidity, sunlight intensity and vehicle amplitude;
establishing an index matrix by using the transportation influence index, collecting real-time index data, filling the index matrix, and outputting the real-time index matrix;
transporting sample data sets corresponding to all indexes through collection histories, analyzing the sample data sets, and generating probability density functions corresponding to all the indexes respectively, wherein the probability density functions are used for defining abnormal change probabilities of the corresponding indexes;
performing index variation probability calculation on the real-time index matrix by using the probability density function to generate a variation index matrix, wherein each index in the variation index matrix corresponds to one variation probability;
performing self-adaptive evolution recognition on the variation index matrix, and outputting a self-adaptive control result, wherein the self-adaptive control result comprises optimized control parameters of all indexes;
the carriage control module is connected, and the self-adaptive control result is input into the carriage control module to control the vehicle for transporting the health care products;
the sample data set is analyzed to generate probability density functions corresponding to the indexes respectively, and the probability density functions comprise:
acquiring attribute information of a health product to be transported, and acquiring a preset influence index according to the attribute information of the health product;
analyzing the sample data set by using the preset influence index, and taking the preset influence index as an abnormal change identification value to obtain a first distribution interval and a second distribution interval, wherein the first distribution interval is an interval smaller than the preset influence index, and the second distribution interval is an interval greater than or equal to the preset influence index;
identifying the distribution of the sample data sets at two ends of the preset influence index according to the first distribution interval and the second distribution interval, and defining a probability density function of the corresponding index according to the probability that the sample data set corresponding to each index is located in the second distribution interval;
the probability density function is expressed as follows:
；
wherein,to represent the probability density function that the ith index obeys a normal distribution over the second distribution interval,adaptive weight corresponding to the ith index, < ->Is a sample data set with the ith index continuously changed, and，/>data of preset influence indexes;
performing adaptive evolution recognition on the variation index matrix, and outputting an adaptive control result, wherein the adaptive evolution recognition comprises the following steps:
taking the minimum variation probability of each data in the variation index matrix as an adaptation target, iterating the data of each index, and outputting a self-adaptive control result;
determining a first index according to the descending rate of each index of the current iteration round in the iteration process, increasing the zooming step length of the first index when the current iteration round is positioned at the next iteration round, and the like until the adaptation target is met, and outputting an adapted index matrix;
and inputting the adaptive control result into the carriage control module for control according to the adaptive index matrix.
2. The method of claim 1, wherein the probability density function is used to perform an index variation probability calculation on the real-time index matrix to generate a variation index matrix, the method comprising:
inputting the data of each index in the real-time index matrix into the probability density function, and generating a first interval by using the data of each index in the real-time index matrix and the preset influence index;
acquiring the integral of each index in the first interval and outputting an integral set;
and marking the variation probability of each index by using the integral set, outputting a variation probability set, and generating a variation index matrix according to the variation probability set.
3. The method of claim 1, wherein the data for each index is iterated using an adaptive scaling factor that decreases in size with increasing number of iterations, the adaptive scaling factor being expressed as:
；
wherein,for the scaling step of the next iteration round, t is the current iteration round, +.>Is->Maximum scaling step of iteration round, +.>Is->Minimum scaling step of iteration round, +.>Is the number of iterations that have been performed.
4. The method of claim 1, wherein a first indicator is determined during an iteration at a rate of decrease of each indicator for a current iteration round, the method further comprising, when at a next iteration round, increasing a scaling step of the first indicator:
judging the association degree of each index in the index matrix, and acquiring the association index of the first index after determining the first index according to the association degree of each index, wherein the association degree of the association index is larger than a preset association degree;
and increasing the scaling step length of the associated index while increasing the scaling step length of the first index in the next iteration round.
5. A system for adaptively controlling a transportation environment for health products, which is configured to implement the method for adaptively controlling a transportation environment for health products according to any one of claims 1 to 4, comprising:
an influence index acquisition unit for acquiring a transportation influence index for transporting the health product, wherein the transportation influence index at least comprises a compartment temperature, a compartment humidity, a sunlight intensity and a vehicle amplitude;
the index matrix establishing unit is used for establishing an index matrix by using the transportation influence index, acquiring real-time index data, filling the index matrix and outputting a real-time index matrix;
the sample data analysis unit is used for transporting sample data sets corresponding to the indexes through collection histories, analyzing the sample data sets and generating probability density functions corresponding to the indexes respectively, wherein the probability density functions are used for defining abnormal change probabilities of the corresponding indexes;
the variation probability calculation unit is used for calculating the index variation probability of the real-time index matrix by utilizing the probability density function to generate a variation index matrix, wherein each index in the variation index matrix corresponds to one variation probability;
the control result output unit is used for carrying out self-adaptive evolution identification on the variation index matrix and outputting a self-adaptive control result, wherein the self-adaptive control result comprises optimized control parameters of each index;
and the vehicle control unit is used for being connected with the carriage control module, inputting the self-adaptive control result into the carriage control module and controlling the vehicle for transporting the health care products.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311402712.1A CN117130265B (en) | 2023-10-27 | 2023-10-27 | Self-adaptive control method and system for health product transportation environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311402712.1A CN117130265B (en) | 2023-10-27 | 2023-10-27 | Self-adaptive control method and system for health product transportation environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117130265A CN117130265A (en) | 2023-11-28 |
| CN117130265B true CN117130265B (en) | 2024-01-02 |
Family
ID=88856809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311402712.1A Active CN117130265B (en) | 2023-10-27 | 2023-10-27 | Self-adaptive control method and system for health product transportation environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117130265B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276488A (en) * | 2019-06-18 | 2019-09-24 | 浙江财经大学 | A kind of vehicle routing optimization method based on matrix in block form and fuzzy haulage time |
| CN111226239A (en) * | 2017-10-16 | 2020-06-02 | 日本电气株式会社 | Transport operation control apparatus, transport operation control system, transport operation control method, and recording medium storing transport operation control program |
| CN115879848A (en) * | 2023-02-20 | 2023-03-31 | 中铁建电气化局集团第三工程有限公司 | Transport vehicle safety monitoring method and device |
| CN116562615A (en) * | 2023-04-12 | 2023-08-08 | 新疆维吾尔自治区产品质量监督检验研究院(新疆维吾尔自治区建筑材料研究院、新疆维吾尔自治区建材非金属产品质量监督检验站) | Risk early warning method for dairy food safety |
| CN116648706A (en) * | 2021-03-02 | 2023-08-25 | 格步计程车控股私人有限公司 | Method and device for controlling a transport system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11327492B2 (en) * | 2019-12-03 | 2022-05-10 | Mitsubishi Electric Research Laboratories, Inc. | Adaptive control of autonomous or semi-autonomous vehicle |
-
2023
- 2023-10-27 CN CN202311402712.1A patent/CN117130265B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111226239A (en) * | 2017-10-16 | 2020-06-02 | 日本电气株式会社 | Transport operation control apparatus, transport operation control system, transport operation control method, and recording medium storing transport operation control program |
| CN110276488A (en) * | 2019-06-18 | 2019-09-24 | 浙江财经大学 | A kind of vehicle routing optimization method based on matrix in block form and fuzzy haulage time |
| CN116648706A (en) * | 2021-03-02 | 2023-08-25 | 格步计程车控股私人有限公司 | Method and device for controlling a transport system |
| CN115879848A (en) * | 2023-02-20 | 2023-03-31 | 中铁建电气化局集团第三工程有限公司 | Transport vehicle safety monitoring method and device |
| CN116562615A (en) * | 2023-04-12 | 2023-08-08 | 新疆维吾尔自治区产品质量监督检验研究院(新疆维吾尔自治区建筑材料研究院、新疆维吾尔自治区建材非金属产品质量监督检验站) | Risk early warning method for dairy food safety |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117130265A (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3938854A1 (en) | Method of performing a process and optimizing control signals used in the process | |
| DE102021201296A1 (en) | Prediction model for predicting product quality parameter values | |
| CN116400126B (en) | Low-voltage power box with data processing system | |
| CN104181883A (en) | Method for processing abnormal data of real-time data acquisition system in real time | |
| CN114463954B (en) | Combustible gas monitoring and early warning system and method based on Internet of things | |
| CN117871771B (en) | Big data-based gas energy monitoring method | |
| CN117195747B (en) | Uniform heat distribution optimization method for magnetic material drying | |
| CN116852665A (en) | Injection molding process parameter intelligent adjusting method based on mixed model | |
| CN117130265B (en) | Self-adaptive control method and system for health product transportation environment | |
| CN114115393A (en) | Method for controlling moisture and temperature at outlet of cut tobacco dryer for sheet cut tobacco making line | |
| CN116225102A (en) | Mobile energy storage communication temperature rise automatic monitoring system and device | |
| CN117873238A (en) | Plant growth control method and system, computer equipment and storage medium | |
| US10379529B2 (en) | Data processing device and data processing method | |
| CN118084098A (en) | Water treatment system and method for intelligent water plant | |
| CN116662729B (en) | Low borosilicate glass feeding control data intelligent monitoring method | |
| US20200019858A1 (en) | Optimization of cyber-physical systems | |
| CN115511188A (en) | Cylinder deterioration analysis method, system, equipment and storage medium | |
| CN117890440B (en) | Semiconductor gas sensor temperature control voltage optimization method based on information entropy | |
| CN118218414B (en) | Cold-rolled plate shape preset control method based on digital twin model | |
| CN117519042B (en) | Intelligent control method, system and storage medium for cement production based on AI technology | |
| CN116765283B (en) | Correction system and method based on cutting, stripping, riveting and screwing integrated machine | |
| CN118655932A (en) | Fascia ball production process control by temperature change monitored control system | |
| CN117978868A (en) | Data acquisition edge aggregation method for Internet of things | |
| EP3923094A1 (en) | Inspection rate adaptation | |
| CN118760271A (en) | Control method and system for intelligent incubator for aerospace biological experiments |
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 |