A case intelligent regulation and control method based on internet of things and an automatic temperature control case system

Abstract

The present application relates to the technical field of intelligent control of machine cases, in particular to an intelligent control method of machine cases based on the Internet of Things and an automatic temperature control machine case system, which compares the preprocessed real-time operation temperature data of the machine case with the preset temperature threshold value, scientifically analyzes whether the real-time operation temperature of the machine case is within the normal range, acquires the real-time operation abnormal temperature data of the machine case when it is not within the normal range, searches for the corresponding real-time operation abnormal position data of the machine case, constructs the real-time abnormal temperature feature data of the machine case based on the real-time operation abnormal temperature data and the real-time operation abnormal position data, accurately searches for the real-time temperature control scheme data of the machine case matched with the real-time abnormal temperature feature data of the machine case through an intelligent optimization algorithm, finally constructs the temperature control data of the machine case, and pushes it to the temperature control platform of the machine case to realize the accurate monitoring and intelligent adjustment of the operation temperature of the machine case.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent regulation and control of machine cases, in particular to an intelligent regulation and control method for machine cases based on the Internet of Things and an automatic temperature control machine case system. BACKGROUND

[0002] With the continuous development of Internet technology, various electronic devices are widely used in many industries. The stability of the operating temperature of the machine case, as an important component of many electronic devices, has an important influence on the working efficiency, service life and safety of the device. However, the existing technology often cannot dynamically adjust the solution according to the real-time operating temperature of the machine case.

[0003] Chinese invention patent with publication number CN108897221B introduces a military power supply machine case fan speed control method. The system model is constructed by combining traditional PID control principle, neural network technology, fuzzy control technology and predictive control technology. The system model is used to comprehensively judge the collected multiple groups of state quantities, predict the temperature of the machine case, and calculate the actual adjustment voltage value of the fan. Based on the actual adjustment voltage value, the speed of the fan is controlled in real time to provide a more accurate and reliable temperature adjustment method to realize stable power supply of the military power supply machine case. However, it can only adjust the temperature of the machine case by controlling the speed of the fan, and cannot select a dynamic solution according to the real-time operating temperature of the machine case. SUMMARY

[0004] To solve the problems in the background art, the present application provides an intelligent regulation and control method for machine cases based on the Internet of Things and an automatic temperature control machine case system, which realizes accurate monitoring and intelligent adjustment of the operating temperature of the machine case.

[0005] An intelligent regulation and control method for machine cases based on the Internet of Things, comprising the following steps:

[0006] S1, collecting real-time operating temperature data of the machine case;

[0007] S2, data preprocessing the real-time operating temperature data of the machine case to generate real-time operating temperature feature data of the machine case;

[0008] S3, setting a temperature threshold, performing numerical comparison processing on the real-time operating temperature feature data of the machine case and the temperature threshold, generating real-time operating temperature analysis data of the machine case according to the numerical comparison result, and if the real-time operating temperature analysis data of the machine case is normal, ending the machine case temperature regulation operation; otherwise, generating real-time operating abnormal temperature data of the machine case;

[0009] S4, performing abnormal temperature position data search processing on the real-time operating abnormal temperature data of the machine case and the machine case temperature monitoring position data to generate real-time operating abnormal position data of the machine case;

[0010] S5, constructing a real-time abnormal temperature feature data of the case based on the real-time running abnormal temperature data of the case and the real-time running abnormal position data of the case;

[0011] S6, establishing a case temperature regulation scheme data, performing real-time temperature regulation scheme matching processing on the real-time abnormal temperature feature data of the case and the case temperature regulation scheme data, and generating a real-time temperature regulation scheme data of the case;

[0012] S7, constructing a case temperature regulation data based on the real-time abnormal temperature feature data of the case and the real-time temperature regulation scheme data of the case, and pushing to a case temperature regulation platform.

[0013] The application compares the pre-processed real-time running temperature data of the case with the preset temperature threshold value, scientifically analyzes whether the real-time running temperature of the case is in the normal range, obtains the real-time running abnormal temperature data of the case when it is not in the normal range, searches out the corresponding real-time running abnormal position data of the case, constructs the real-time abnormal temperature feature data of the case based on the real-time running abnormal temperature data of the case and the real-time running abnormal position data of the case, accurately searches out the real-time temperature regulation scheme data of the case matched with the real-time abnormal temperature feature data of the case through an intelligent optimization algorithm, finally constructs the case temperature regulation data, and pushes to the case temperature regulation platform, so as to realize accurate monitoring and intelligent adjustment of the running temperature of the case. Preferably, the specific steps of collecting the real-time running temperature data of the case are as follows:

[0014] S11, establishing a case temperature monitoring position data set A={a1, a2,...,a i ,…,a k}, wherein a i represents the position data corresponding to the i th case temperature monitoring area, k represents the total number of case temperature monitoring areas, and the case temperature monitoring area includes but is not limited to CPU, mainboard chipset, graphics card and hard disk;

[0015] S12, installing a temperature sensor at the position corresponding to each case temperature monitoring position data in the case temperature monitoring position data set, wherein the temperature sensor represents one of a thermistor temperature sensor, a resistance temperature detector and an IC temperature sensor;

[0016] S13, setting a case temperature monitoring period, dividing the case temperature monitoring period into a plurality of case temperature monitoring time points to obtain a case temperature monitoring time point set B={b1, b2,...,b i ,…,b l}, wherein b irepresents the i-th cabinet temperature monitoring time point obtained after uniform division of the cabinet temperature monitoring period, and l represents the total number of cabinet temperature monitoring time points;

[0017] S14, collecting the running temperature data corresponding to each cabinet temperature monitoring position data in the cabinet temperature monitoring position data set at each cabinet temperature monitoring time point in the cabinet temperature monitoring time point set by each temperature sensor in real time to obtain a cabinet real-time running temperature data matrix C as follows: ,

[0018] wherein, c ij represents the running temperature data corresponding to the j-th cabinet temperature monitoring area at the i-th cabinet temperature monitoring time point collected by the temperature sensor in real time.

[0019] Preferably, the cabinet real-time running temperature data is preprocessed to generate cabinet real-time running temperature feature data, and the specific steps are as follows:

[0020] S21, performing abnormal data cleaning processing on the cabinet real-time running temperature data in the cabinet real-time running temperature data matrix by the quartile interval method to generate a cabinet real-time running temperature real data matrix as follows: ,

[0021] wherein, c ij represents the cabinet real-time running temperature real data obtained after abnormal data cleaning processing of the running temperature data corresponding to the i-th cabinet temperature monitoring area at the j-th cabinet temperature monitoring time point collected by the temperature sensor in real time; the abnormal data cleaning processing process is as follows:

[0022] S211, arranging the i-th row of cabinet real-time running temperature data in the cabinet real-time running temperature data matrix from small to large to obtain a data sequence, and calculating the lower quartile , the median and the upper quartile of the data sequence, respectively;

[0023] S212, if , it is determined that c ij is cabinet real-time running temperature real data, and c ij is retained; otherwise, it is determined that c ij is an abnormal point of cabinet real-time running temperature data, and the median is used to replace c ij ;

[0024] S213, repeat the operations in S211 to S212 until all the chassis real-time running temperature data in the chassis real-time running temperature data matrix are traversed, and generate a chassis real-time running temperature real data matrix;

[0025] S22, perform average numerical measurement processing on the chassis real-time running temperature real data in the chassis real-time running temperature real data matrix by using a mean formula, and generate a chassis real-time running temperature feature data set , wherein, represents the chassis real-time running temperature feature data corresponding to the i-th chassis temperature monitoring area, and .

[0026] The quartile interval method is used to accurately identify the abnormal temperature data in the chassis real-time running temperature data matrix, and a suitable value is selected for replacement, which effectively avoids the influence of errors in the data acquisition process, ensures the reliability of the obtained data, and uses the mean formula to perform average numerical measurement processing on the chassis real-time running temperature real data in the chassis real-time running temperature real data matrix, integrates multiple real data into one value, and provides a data basis for subsequent analysis of the chassis temperature state.

[0027] Preferably, a temperature threshold is set, the chassis real-time running temperature feature data and the temperature threshold are compared in value, and chassis real-time running temperature analysis data is generated according to the value comparison result. If the chassis real-time running temperature analysis data is normal, the chassis temperature regulation work is ended; otherwise, the specific steps of generating chassis real-time running abnormal temperature data are as follows:

[0028] S31, set a temperature threshold, and sequentially compare each chassis real-time running temperature feature data in the chassis real-time running temperature feature data set with the temperature threshold in value, and generate chassis real-time running temperature analysis data D fenxi according to the value comparison result;

[0029] If all the chassis real-time running temperature feature data in the chassis real-time running temperature feature data set are less than the temperature threshold, the chassis real-time running temperature analysis data D fenxi is output as normal, the chassis real-time running temperature analysis data D fenxi is pushed to the chassis temperature regulation platform through a communication network, and the chassis temperature regulation work is ended;

[0030] If any one of the chassis real-time running temperature feature data in the chassis real-time running temperature feature data set is greater than the temperature threshold, the chassis real-time running temperature analysis data D fenxiFor anomaly, all cabinet real-time running temperature feature data greater than the temperature threshold value in the cabinet real-time running temperature feature data set is screened out and data identification is performed to generate a cabinet real-time running abnormal temperature data set wherein, represents the i th cabinet real-time running abnormal temperature data, and p represents the total number of cabinet real-time running abnormal temperature data.

[0031] By comparing the preset temperature threshold value with the cabinet real-time running temperature feature data, the temperature state of the cabinet is analyzed in real time, and a preliminary determination is made for intelligent control of the cabinet temperature. When the cabinet temperature state is not in the normal range, the cabinet real-time running abnormal temperature data is scientifically screened out.

[0032] Preferably, the cabinet real-time running abnormal temperature data and the cabinet temperature monitoring position data are subjected to abnormal temperature position data search processing to generate the specific steps of the cabinet real-time running abnormal position data as follows:

[0033] S41, all cabinet temperature monitoring position data in the cabinet temperature monitoring position data set is traversed by an iterative deepening search algorithm, and cabinet temperature monitoring position data matched with each cabinet real-time running abnormal temperature data in the cabinet real-time running abnormal temperature data set is searched and data identification is performed to generate a cabinet real-time running abnormal position data set E={e1, e2, …, e i ,…,e p}, wherein, represents the i th cabinet real-time running abnormal temperature data corresponding position data.

[0034] By using the iterative deepening search algorithm, the cabinet temperature monitoring position data matched with the cabinet real-time running abnormal temperature data is accurately searched to generate the cabinet real-time running abnormal position data, and the cabinet position where the temperature anomaly occurs and the corresponding temperature data are accurately identified.

[0035] Preferably, the specific steps of constructing the cabinet real-time abnormal temperature feature data based on the cabinet real-time running abnormal temperature data and the cabinet real-time running abnormal position data are as follows:

[0036] S51, each cabinet real-time running abnormal temperature data in the cabinet real-time running abnormal temperature data set is combined with the corresponding cabinet real-time running abnormal position data in the cabinet real-time running abnormal position data set to generate a cabinet real-time abnormal temperature feature data set wherein, represents the i th cabinet real-time abnormal temperature feature data, and .

[0037] Preferably, the specific steps for establishing chassis temperature control scheme data, and matching the real-time abnormal temperature characteristic data of the chassis with the chassis temperature control scheme data to generate real-time chassis temperature control scheme data, are as follows:

[0038] S61. Establish a chassis temperature control scheme dataset F={f1,f2,…,f i ,…,f o}, where f i This represents the i-th chassis temperature control scheme data, and o represents the total number of chassis temperature control scheme data. The chassis temperature control scheme data represents the fan selection for performing chassis temperature control operations and the corresponding speed of each fan. The fans include intake fans and exhaust fans.

[0039] S62. Using the White Whale optimization algorithm, perform real-time temperature control scheme matching processing on each chassis temperature control scheme data in the chassis real-time abnormal temperature feature dataset and the chassis temperature control scheme dataset. Search for chassis temperature control scheme data that matches the chassis real-time abnormal temperature feature dataset and identify the data, generating chassis real-time temperature control scheme data F. fangan ;

[0040] S621. Construct a control scheme to search for beluga whale populations, setting the population size as N, the current iteration count as t, and the maximum iteration count as t. max And the data search space dimension for chassis temperature control solutions is P;

[0041] The chassis temperature control scheme dataset is used as the chassis temperature control scheme data search space. N chassis temperature control scheme data are randomly generated in the chassis temperature control scheme data search space. Each chassis temperature control scheme data corresponds to a beluga whale individual in the beluga whale population for which the control scheme is searched.

[0042] S622. Calculate the fitness value of each beluga whale individual in the beluga whale population for which the control scheme is being searched. Arrange the beluga whale individuals in the beluga whale population for which the control scheme is being searched according to their fitness values ​​from largest to smallest, and select the beluga whale individual with the highest fitness value as the current optimal individual. The fitness value calculation formula is as follows: ,

[0043] Among them, Fit i x represents the fitness value of the i-th beluga whale individual in the beluga whale population for which the proposed control scheme is searched. i v represents the control cost of searching for the chassis temperature control scheme data corresponding to the i-th beluga whale individual in the beluga whale population using the control scheme search. irepresents the average cooling speed of the incubator temperature regulation scheme data corresponding to the i-th regulation scheme search beluga whale individual in the regulation scheme search beluga whale population;

[0044] S623、the regulation scheme search beluga whale individual in the regulation scheme search beluga whale population controls its own swimming behavior in the incubator temperature regulation scheme data search space through the balance factor The balance factor update formula is as follows: ,

[0045] , represents the balance factor in the current iteration process, and rand represents a random number subject to uniform distribution between (0, 1);

[0046] If the balance factor is greater than 0.5, the regulation scheme search beluga whale individual in the regulation scheme search beluga whale population will adopt a mirror swimming strategy, and perform position update with a randomly selected regulation scheme search beluga whale individual in the incubator temperature regulation scheme data search space through the method of swimming in the same direction; the position update formula is as follows: ,

[0047] , represents the position of the i-th regulation scheme search beluga whale individual in the regulation scheme search beluga whale population after position update in the j-th dimension incubator temperature regulation scheme data search space, and respectively represent the current positions of the z-th and i-th regulation scheme search beluga whale individuals in the regulation scheme search beluga whale population in the j-th dimension incubator temperature regulation scheme data search space, and r1 and r2 both represent random numbers subject to uniform distribution between (0, 1);

[0048] If the balance factor is less than or equal to 0.5, the regulation scheme search beluga whale individual in the regulation scheme search beluga whale population will share prey position information, and perform position update in the incubator temperature regulation scheme data search space through the method of cooperative hunting of the optimal prey; the position update formula is as follows: ,

[0049] , represents the position of the i-th regulation scheme search beluga whale individual in the regulation scheme search beluga whale population after position update, r3 and r4 both represent random numbers subject to uniform distribution between (0, 1), and X best represents the position of the current optimal individual, and wherein, z and i represent the current positions of the zth and ith regulatory scheme search white whale individuals in the regulatory scheme search white whale population, ε represents a Levy flight function, γ represents a random jump strength of the Levy flight, and ;

[0050] S624, updating the whale fall probability ω of each regulatory scheme search white whale individual in the regulatory scheme search white whale population; the updating formula is as follows: ,

[0051] S625, each regulatory scheme search white whale individual in the regulatory scheme search white whale population performs a whale fall behavior in the cabinet temperature regulation scheme data search space for position updating according to the whale fall probability ω; the position updating formula is as follows: ,

[0052] wherein, r5, r6 and r7 each represent a random number subject to uniform distribution between (0, 1), X step represents a whale fall step length;

[0053] S626, calculating the fitness value of each regulatory scheme search white whale individual in the regulatory scheme search white whale population after position updating; if the fitness value of the regulatory scheme search white whale individual after position updating is greater than the fitness value of the original position, the new position is used to replace the original position; otherwise, the original position is retained;

[0054] rearranging each regulatory scheme search white whale individual in the regulatory scheme search white whale population according to the fitness value from large to small, and selecting the regulatory scheme search white whale individual with the highest fitness value as a new current optimal individual;

[0055] S627, judging whether the current iteration number t is less than the maximum iteration number t max ; if the current iteration number t is less than the maximum iteration number t max , the current iteration number t is increased by 1, and returning to S623; otherwise, the current optimal individual is taken as a global optimal solution, the cabinet temperature regulation scheme data corresponding to the global optimal solution is outputted and data identification is performed, and cabinet real-time temperature regulation scheme data F fangan is generated.

[0056] The white whale optimization algorithm is used for real-time temperature regulation scheme matching processing of the cabinet real-time abnormal temperature characteristic data and the cabinet temperature regulation scheme data, so that a temperature regulation scheme conforming to the current cabinet temperature state is quickly and accurately searched out, and the white whale optimization algorithm has good robustness and can ensure the stability of the matching process.

[0057] Preferably, based on the case real-time abnormal temperature characteristic data and the case real-time temperature regulation scheme data, case temperature regulation data is constructed, and the specific steps of pushing to the case temperature regulation platform are as follows:

[0058] S71, the case real-time abnormal temperature characteristic data set And the case real-time temperature regulation scheme data F fangan Data combination is performed to construct case temperature regulation data ;

[0059] S72, the case temperature regulation data Is pushed to the case temperature regulation platform through a communication network, and case temperature regulation work is performed.

[0060] The application also includes an automatic temperature control case system based on the Internet of Things, comprising a case real-time running temperature data acquisition module, a case real-time running temperature data preprocessing module, a case real-time running temperature analysis module, a case real-time running abnormal position search module, a case real-time abnormal temperature characteristic data construction module, a case real-time temperature regulation scheme matching module, and a case temperature regulation data construction module.

[0061] The case real-time running temperature data acquisition module acquires real-time running temperature data corresponding to each case temperature monitoring position data at each case temperature monitoring time point through a plurality of temperature sensors installed, to obtain case real-time running temperature data.

[0062] The case real-time running temperature data preprocessing module performs abnormal data cleaning processing on the case real-time running temperature data through the quartile interval method to generate case real-time running temperature real data, and then performs average value measurement processing on the case real-time running temperature real data using the mean formula to generate case real-time running temperature characteristic data.

[0063] The case real-time running temperature analysis module performs numerical comparison processing of the case real-time running temperature characteristic data with the temperature threshold value in sequence by setting the temperature threshold value, generates case real-time running temperature analysis data according to the numerical comparison result, and if the case real-time running temperature analysis data is normal, ends the case temperature regulation work; otherwise, generates case real-time running abnormal temperature data.

[0064] The case real-time running abnormal position search module searches for case temperature monitoring position data matched with the case real-time running abnormal temperature data and performs data identification by traversing the case temperature monitoring position data through an iterative deepening search algorithm to generate case real-time running abnormal position data.

[0065] The chassis real-time abnormal temperature feature data construction module constructs chassis real-time abnormal temperature feature data by data combination of the chassis real-time running abnormal temperature data and the chassis real-time running abnormal position data;

[0066] The chassis real-time temperature regulation scheme matching module searches out chassis temperature regulation scheme data matched with the chassis real-time abnormal temperature feature data and performs data identification through real-time temperature regulation scheme matching processing of the chassis real-time abnormal temperature feature data and the established chassis temperature regulation scheme data by the beluga whale optimization algorithm, and generates chassis real-time temperature regulation scheme data.

[0067] The chassis temperature regulation data construction module constructs chassis temperature regulation data by data combination of the chassis real-time abnormal temperature feature data set and the chassis real-time temperature regulation scheme data, pushes the chassis temperature regulation data to a chassis temperature regulation platform through a communication network, and executes a chassis temperature regulation job.

[0068] 1、The application compares the preprocessed chassis real-time running temperature data with a preset temperature threshold value, scientifically analyzes whether the real-time running temperature of the chassis is in a normal range, obtains chassis real-time running abnormal temperature data when the real-time running temperature is not in the normal range, searches out corresponding chassis real-time running abnormal position data, constructs chassis real-time abnormal temperature feature data based on the chassis real-time running abnormal temperature data and the chassis real-time running abnormal position data, accurately searches out chassis real-time temperature regulation scheme data matched with the chassis real-time abnormal temperature feature data through an intelligent optimization algorithm, finally constructs chassis temperature regulation data, and pushes the chassis temperature regulation data to a chassis temperature regulation platform, so as to realize accurate monitoring and intelligent adjustment of the chassis running temperature.

[0069] 2、The quartile interval method is used to accurately identify abnormal temperature data in the chassis real-time running temperature data matrix, and appropriate numerical values are selected for replacement, so as to effectively avoid the influence of errors in the data acquisition process and ensure the reliability of the obtained data. The mean value formula is used for average numerical value measurement processing of the chassis real-time running temperature real data in the chassis real-time running temperature real data matrix, a plurality of real data is integrated into one numerical value, and a data basis is provided for subsequent analysis of the chassis temperature state.

[0070] 3, by preset temperature threshold and the chassis real-time operation temperature characteristic data numerical comparison, real-time analysis of the temperature state of the chassis, for the intelligent regulation of the chassis temperature has made a preliminary determination, when the chassis temperature state is not in the normal range, scientific screening out the chassis real-time operation abnormal temperature data, and through the iterative deep search algorithm accurate search out the chassis temperature monitoring position data matched with the chassis real-time operation abnormal temperature data, generate chassis real-time operation abnormal position data, accurately identify the chassis position and the corresponding temperature data that appear temperature abnormal;

[0071] 4, by white whale optimization algorithm to the chassis real-time abnormal temperature characteristic data and the chassis temperature regulation scheme data real-time temperature regulation scheme matching processing, quickly and accurately search out the temperature regulation scheme that meets the current chassis temperature state, while the white whale optimization algorithm has good robustness, can ensure the stability of the matching process. BRIEF DESCRIPTION OF DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, the drawings obtained from these drawings can also be obtained without creative labor.

[0073] Figure 1 The flow chart of the intelligent regulation method of the chassis based on the Internet of Things provided by the application;

[0074] Figure 2 The module schematic diagram of the automatic temperature control chassis system based on the Internet of Things provided by the application. DETAILED DESCRIPTION

[0075] The technical solutions in the embodiments of the application will be described clearly and completely in the following with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0076] In the description of the application, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner" and the like indicate the orientation or positional relationship, which are only for the convenience of describing the application and simplifying the description, and do not indicate or imply that the components or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, therefore it cannot be understood as a limitation of the application.

[0077] Embodiment one is as follows:

[0078] Please refer toFigure 1 An intelligent control method for a case based on the Internet of Things, comprising the following steps:

[0079] S1, collecting real-time running temperature data of the case;

[0080] S11, establishing a case temperature monitoring position data set A={a1, a2,…,a i ,…,a k}, wherein a i represents the position data corresponding to the i-th case temperature monitoring area, and k represents the total number of case temperature monitoring areas, which includes but is not limited to CPU, mainboard chipset, graphics card and hard disk;

[0081] S12, installing a temperature sensor at the position corresponding to each case temperature monitoring position data in the case temperature monitoring position data set, wherein the temperature sensor is one of a thermistor temperature sensor, a resistance temperature detector and an IC temperature sensor;

[0082] S13, setting a case temperature monitoring period, dividing the case temperature monitoring period into several case temperature monitoring time points to obtain a case temperature monitoring time point set B={b1, b2,…,b i ,…,b l}, wherein b i represents the i-th case temperature monitoring time point obtained by uniformly dividing the case temperature monitoring period, and l represents the total number of case temperature monitoring time points;

[0083] S14, collecting real-time running temperature data corresponding to each case temperature monitoring position data in the case temperature monitoring position data set at each case temperature monitoring time point in the case temperature monitoring time point set by each temperature sensor to obtain a case real-time running temperature data matrix C as follows: ,

[0084] wherein c ij represents the running temperature data corresponding to the j-th case temperature monitoring area collected by the temperature sensor at the i-th case temperature monitoring time point.

[0085] S2, data preprocessing of the case real-time running temperature data to generate case real-time running temperature feature data;

[0086] S21, cleaning abnormal data of the case real-time running temperature data in the case real-time running temperature data matrix by quartile interval method to generate a case real-time running temperature real data matrix as follows: ,

[0087] wherein c ij represents the real-time running temperature data of the i-th cabinet temperature monitoring area obtained by cleaning the abnormal data of the running temperature data of the i-th cabinet temperature monitoring area collected by the temperature sensor at the j-th cabinet temperature monitoring time point; the abnormal data cleaning process is as follows:

[0088] S211, arranging the i-th row of real-time running temperature data of the cabinet in the real-time running temperature data matrix from small to large to obtain a data sequence, and calculating the lower quartile , the median , and the upper quartile of the data sequence, respectively;

[0089] S212, if , it is determined that c ij is the real-time running temperature data of the cabinet, and c ij is retained; otherwise, it is determined that c ij is an abnormal point of the real-time running temperature data of the cabinet, and c ij is replaced by the median ;

[0090] S213, repeating the operations in S211 to S212 until all real-time running temperature data of the cabinet in the real-time running temperature data matrix is traversed, and generating a real-time running temperature data matrix of the cabinet;

[0091] S22, performing average value measurement processing on the real-time running temperature data of the cabinet in the real-time running temperature data matrix of the cabinet by using the mean formula , and generating a real-time running temperature feature data set of the cabinet , wherein represents the real-time running temperature feature data of the i-th cabinet temperature monitoring area, and .

[0092] S3, setting a temperature threshold, performing numerical comparison processing on the real-time running temperature feature data of the cabinet and the temperature threshold, generating real-time running temperature analysis data of the cabinet according to the numerical comparison result, and ending the cabinet temperature regulation operation if the real-time running temperature analysis data of the cabinet is normal; otherwise, generating real-time running abnormal temperature data of the cabinet;

[0093] S31, setting a temperature threshold, sequentially performing numerical comparison processing on each real-time running temperature feature data in the real-time running temperature feature data set of the cabinet and the temperature threshold, and generating real-time running temperature analysis data D fenxi of the cabinet according to the numerical comparison result;

[0094] If all the cabinet real-time running temperature characteristic data in the set of cabinet real-time running temperature characteristic data are less than the temperature threshold value, the cabinet real-time running temperature analysis data D is output fenxi is normal, and the cabinet real-time running temperature analysis data D is pushed to a cabinet temperature regulation platform through a communication network, and the cabinet temperature regulation operation is ended. fenxi

[0095] If any one of the cabinet real-time running temperature characteristic data in the set of cabinet real-time running temperature characteristic data is greater than the temperature threshold value, the cabinet real-time running temperature analysis data D is output fenxi is abnormal, and all the cabinet real-time running temperature characteristic data greater than the temperature threshold value in the set of cabinet real-time running temperature characteristic data are screened out and identified, to generate a set of cabinet real-time running abnormal temperature data , wherein represents the i th cabinet real-time running abnormal temperature data, and p represents the total number of the cabinet real-time running abnormal temperature data. S4, the cabinet real-time running abnormal temperature data and cabinet temperature monitoring position data are subjected to abnormal temperature position data search processing, to generate cabinet real-time running abnormal position data;

[0096] S41, all the cabinet temperature monitoring position data in the set of cabinet temperature monitoring position data are traversed through an iterative deepening search algorithm, to search out the cabinet temperature monitoring position data matched with each cabinet real-time running abnormal temperature data in the set of cabinet real-time running abnormal temperature data and identify the data, to generate a set of cabinet real-time running abnormal position data E={e1, e2, …, e i , …, e p , wherein represents the i th cabinet real-time running abnormal temperature data corresponding position data.

[0097] S5, the cabinet real-time running abnormal temperature characteristic data is constructed based on the cabinet real-time running abnormal temperature data and the cabinet real-time running abnormal position data;

[0098] S51, each cabinet real-time running abnormal temperature data in the set of cabinet real-time running abnormal temperature data is combined with the corresponding cabinet real-time running abnormal position data in the set of cabinet real-time running abnormal position data, to generate a set of cabinet real-time abnormal temperature characteristic data , wherein represents the i th cabinet real-time abnormal temperature characteristic data, and .

[0099] ​S6. Establish chassis temperature control scheme data, and perform real-time temperature control scheme matching processing on the chassis real-time abnormal temperature characteristic data and the chassis temperature control scheme data to generate chassis real-time temperature control scheme data.

[0100] S61. Establish a chassis temperature control scheme dataset F={f1,f2,…,f i ,…,f o}, where f i This represents the i-th chassis temperature control scheme data, and o represents the total number of chassis temperature control scheme data. The chassis temperature control scheme data represents the fan selection for performing chassis temperature control operations and the corresponding speed of each fan. The fans include intake fans and exhaust fans.

[0101] S62. Using the White Whale optimization algorithm, perform real-time temperature control scheme matching processing on each chassis temperature control scheme data in the chassis real-time abnormal temperature feature dataset and the chassis temperature control scheme dataset. Search for chassis temperature control scheme data that matches the chassis real-time abnormal temperature feature dataset and identify the data, generating chassis real-time temperature control scheme data F. fangan ;

[0102] S621. Construct a control scheme to search for beluga whale populations, setting the population size as N, the current iteration count as t, and the maximum iteration count as t. max And the data search space dimension for chassis temperature control solutions is P;

[0103] The chassis temperature control scheme dataset is used as the chassis temperature control scheme data search space. N chassis temperature control scheme data are randomly generated in the chassis temperature control scheme data search space. Each chassis temperature control scheme data corresponds to a beluga whale individual in the beluga whale population for which the control scheme is searched.

[0104] S622. Calculate the fitness value of each beluga whale individual in the beluga whale population for which the control scheme is being searched. Arrange the beluga whale individuals in the beluga whale population for which the control scheme is being searched according to their fitness values ​​from largest to smallest, and select the beluga whale individual with the highest fitness value as the current optimal individual. The fitness value calculation formula is as follows: ,

[0105] Among them, Fit i x represents the fitness value of the i-th beluga whale individual in the beluga whale population for which the proposed control scheme is searched. i v represents the control cost of searching for the chassis temperature control scheme data corresponding to the i-th beluga whale individual in the beluga whale population using the control scheme search. iThis represents the average cooling rate of the chassis temperature control scheme data corresponding to the i-th beluga whale individual in the beluga whale population searched by the control scheme.

[0106] S623, The aforementioned control scheme searches for individual beluga whales within the beluga whale population using various control schemes through a balance factor. The system controls its swimming behavior within the data search space of the chassis temperature control scheme; the balance factor update formula is as follows: ,

[0107] in, This represents the balance factor in the current iteration process, and rand represents a random number that follows a uniform distribution between (0,1).

[0108] If the balance factor If the value is greater than 0.5, then each beluga whale individual in the beluga whale population will adopt a mirror swimming strategy, updating its position in the chassis temperature control scheme data search space by swimming in the same direction with a randomly selected beluga whale individual; the position update formula is as follows: ,

[0109] in, This represents the position of the i-th beluga whale individual in the beluga whale population after its position has been updated in the j-dimensional data search space for chassis temperature control schemes. and Let r1 and r2 represent the current positions of the z-th and i-th beluga whale individuals in the j-th dimension of the beluga whale population, respectively, and r1 and r2 both represent random numbers uniformly distributed between (0,1).

[0110] If the balance factor If the value is less than or equal to 0.5, then the individual beluga whales in the beluga whale population will share prey location information and update their positions in the chassis temperature control scheme data search space by cooperating to hunt the optimal prey; the position update formula is as follows: ,

[0111] in, This represents the position of the i-th beluga whale individual in the beluga whale population after the position update, where r3 and r4 both represent random numbers uniformly distributed between (0,1). best This indicates the position of the current best individual. and respectively represent the current positions of the zth and ith regulatory scheme search white whale individuals in the white whale population, ε represents a Levy flight function, γ represents the random jump strength of the Levy flight, and ;

[0112] S624, update the whale fall probability ω of each regulatory scheme search white whale individual in the regulatory scheme search white whale population; the update formula is as follows: ,

[0113] S625, each regulatory scheme search white whale individual in the regulatory scheme search white whale population performs whale fall behavior in the cabinet temperature regulation scheme data search space according to the whale fall probability ω for position updating; the position updating formula is as follows: ,

[0114] wherein r5, r6 and r7 all represent random numbers subject to uniform distribution between (0, 1), X step represents a whale fall step length;

[0115] S626, calculate the fitness value of each regulatory scheme search white whale individual in the regulatory scheme search white whale population after position updating, if the fitness value of the regulatory scheme search white whale individual after position updating is greater than the fitness value of the original position, replace the original position with the new position; otherwise, keep the original position;

[0116] rearrange each regulatory scheme search white whale individual in the regulatory scheme search white whale population according to the fitness value from large to small, and select the regulatory scheme search white whale individual with the highest fitness value as a new current optimal individual;

[0117] S627, judge whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max , then the current iteration number t is increased by 1, and return to S623; otherwise, take the current optimal individual as a global optimal solution, output the cabinet temperature regulation scheme data corresponding to the global optimal solution and perform data identification, and generate cabinet real-time temperature regulation scheme data F fangan .

[0118] S7, construct cabinet temperature regulation data based on the cabinet real-time abnormal temperature feature data and the cabinet real-time temperature regulation scheme data, and push to a cabinet temperature regulation platform;

[0119] S71, combine the cabinet real-time abnormal temperature feature data set and the cabinet real-time temperature regulation scheme data F fangan to construct cabinet temperature regulation data ;

[0120] S72, transmitting the cabinet temperature regulation data through a communication network to a cabinet temperature regulation platform and performing a cabinet temperature regulation operation.

[0121] Embodiment two is as follows:

[0122] Please refer to Figure 2 An automatic temperature control cabinet system based on the Internet of Things, comprising a cabinet real-time running temperature data acquisition module, a cabinet real-time running temperature data preprocessing module, a cabinet real-time running temperature analysis module, a cabinet real-time running abnormal position search module, a cabinet real-time abnormal temperature feature data construction module, a cabinet real-time temperature regulation scheme matching module, and a cabinet temperature regulation data construction module.

[0123] The cabinet real-time running temperature data acquisition module acquires real-time running temperature data of each cabinet temperature monitoring position data at each cabinet temperature monitoring time point through a plurality of temperature sensors installed.

[0124] The cabinet real-time running temperature data preprocessing module performs abnormal data cleaning processing on the cabinet real-time running temperature data by quartile interval method to generate cabinet real-time running temperature real data, and then performs average value measurement processing on the cabinet real-time running temperature real data by mean formula to generate cabinet real-time running temperature feature data.

[0125] The cabinet real-time running temperature analysis module compares the cabinet real-time running temperature feature data with the temperature threshold value in sequence by setting the temperature threshold value, generates cabinet real-time running temperature analysis data according to the numerical comparison result, and if the cabinet real-time running temperature analysis data is normal, ends the cabinet temperature regulation operation; otherwise, generates cabinet real-time running abnormal temperature data.

[0126] The cabinet real-time running abnormal position search module searches for cabinet temperature monitoring position data matched with the cabinet real-time running abnormal temperature data and performs data identification by traversing the cabinet temperature monitoring position data through an iterative deep search algorithm to generate cabinet real-time running abnormal position data.

[0127] The cabinet real-time abnormal temperature feature data construction module constructs cabinet real-time abnormal temperature feature data by combining the cabinet real-time running abnormal temperature data and the cabinet real-time running abnormal position data.

[0128] ​The cabinet real-time temperature regulation scheme matching module performs real-time temperature regulation scheme matching processing on the cabinet real-time abnormal temperature characteristic data and the established cabinet temperature regulation scheme data through the beluga whale optimization algorithm, searches for cabinet temperature regulation scheme data matched with the cabinet real-time abnormal temperature characteristic data, and performs data identification, to generate cabinet real-time temperature regulation scheme data;

[0129] The cabinet temperature regulation data construction module combines the cabinet real-time abnormal temperature characteristic data set and the cabinet real-time temperature regulation scheme data, constructs cabinet temperature regulation data, pushes the cabinet temperature regulation data to a cabinet temperature regulation platform through a communication network, and performs a cabinet temperature regulation operation.

[0130] In the description of the present specification, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0131] The preferred embodiments of the above disclosed invention are only used to help explain the invention. The preferred embodiments do not describe all the details and limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can well understand and utilize the invention.

Claims

1. An Internet of Things-based cabinet intelligent regulation method, characterized in that, The method comprises the following steps: S1, collecting real-time operation temperature data of the case; S2, performing data preprocessing on the real-time operation temperature data of the case, including performing abnormal data cleaning processing on the real-time operation temperature data of the case by using the quartile interval method to generate case real-time operation temperature feature data; S3, setting a temperature threshold, performing numerical comparison processing on the case real-time operation temperature feature data and the temperature threshold, generating case real-time operation temperature analysis data according to the numerical comparison result, if the case real-time operation temperature analysis data is normal, ending the case temperature regulation operation; otherwise, generating case real-time operation abnormal temperature data; S4, performing abnormal temperature position data search processing on the case real-time operation abnormal temperature data and the case temperature monitoring position data to generate case real-time operation abnormal position data; S5, constructing case real-time abnormal temperature feature data based on the case real-time operation abnormal temperature data and the case real-time operation abnormal position data; S6, establishing case temperature regulation scheme data, performing real-time temperature regulation scheme matching processing on the case real-time abnormal temperature feature data and the case temperature regulation scheme data to generate case real-time temperature regulation scheme data; S7, constructing case temperature regulation data based on the case real-time abnormal temperature feature data and the case real-time temperature regulation scheme data, and pushing the case temperature regulation data to a case temperature regulation platform; Wherein, S4 includes S41, traversing all cabinet temperature monitoring position data in A through iterative deepening search algorithm, searching out cabinet temperature monitoring position data matched with each cabinet real-time running abnormal temperature data in and performing data identification, generating cabinet real-time running abnormal position data set E={e1, e2, …, e i , …,e p}, represents the position data corresponding to the i th cabinet real-time running abnormal temperature data, and the cabinet position and the corresponding temperature data where the temperature anomaly occurs are accurately identified; S5 includes S51, combining each cabinet real-time running abnormal temperature data in with the corresponding cabinet real-time running abnormal position data in E to generate cabinet real-time abnormal temperature feature data set , wherein, represents the i th cabinet real-time abnormal temperature feature data, and ; S3 includes: S31, setting a temperature threshold, The real-time operating temperature characteristic data of each chassis are sequentially compared with temperature thresholds, and the real-time operating temperature analysis data D of the chassis is generated based on the comparison results. fenxi ;like If all the real-time operating temperature characteristics of the chassis are less than the temperature threshold, then the output D is... fenxi For normal operation, D will be transmitted via the communication network. fenxi Push to the chassis temperature control platform and end this chassis temperature control operation; if If the real-time operating temperature characteristic data of any chassis in the system is greater than the temperature threshold, then output D. fenxi If it is an anomaly, filter it out. Real-time operating temperature characteristic data of all chassis exceeding the temperature threshold are collected and labeled to generate a dataset of abnormal real-time operating temperatures of chassis. ,in, This represents the real-time abnormal temperature data of the i-th chassis, and p represents the total number of real-time abnormal temperature data of the chassis. 2.The intelligent regulation method of the case based on the Internet of Things according to claim 1, characterized in that, S1 comprises the following steps: S11. Establish a chassis temperature monitoring location dataset A={a1,a2,a...} i ,…,a k }, where a i This represents the location data corresponding to the i-th chassis temperature monitoring area, and k represents the total number of chassis temperature monitoring areas; S12, installing temperature sensors at positions corresponding to each case temperature monitoring position data in A; S13, set the case temperature monitoring period, divide the case temperature monitoring period into several case temperature monitoring time points evenly, obtain a case temperature monitoring time point set B={b1, b2, …, b i ,…,b l}, wherein b i represents the i-th case temperature monitoring time point obtained after the case temperature monitoring period is evenly divided, and l represents the total number of case temperature monitoring time points; S14, collecting real-time operation temperature data of each case temperature monitoring position data in A at each case temperature monitoring time point in B through each temperature sensor to obtain a case real-time operation temperature data matrix C as follows: ， wherein c ij represents the operating temperature data corresponding to the jth cabinet temperature monitoring area collected by the temperature sensor at the ith cabinet temperature monitoring time point. 3.The intelligent regulation method of the case based on the Internet of Things according to claim 2, characterized in that, S2 comprises the following steps: S21, through the quartile interval method, the real-time running temperature data of the chassis in C is processed to remove abnormal data, and a real-time running temperature data matrix of the chassis is generated As follows: ， wherein, represents the real-time operating temperature data of the i-th cabinet temperature monitoring area obtained by cleaning the abnormal data of the operating temperature data of the i-th cabinet temperature monitoring area corresponding to the j-th cabinet temperature monitoring time point collected by the temperature sensor; the abnormal data cleaning process is as follows: S211. Arrange the real-time chassis operating temperature data in the i-th row of C from smallest to largest to obtain a data sequence, and calculate the lower quartile of the data sequence. , median and upper quartiles ; S212, if c ij is determined to be a real data of the real-time running temperature of the machine case, c ij is retained; otherwise, c ij is determined to be an abnormal point of the real-time running temperature data of the machine case, and c is replaced by the median ij ; S213, repeat the operations in S211 to S212 until all the chassis real-time running temperature data in C are traversed, and generate ; S22. Using the mean formula to... The real-time operating temperature data of the chassis is averaged and processed to generate a real-time operating temperature feature dataset of the chassis. ,in, This represents the real-time operating temperature characteristic data of the chassis corresponding to the i-th chassis temperature monitoring area, and .

4. The intelligent regulation and control method for a case based on the Internet of Things according to claim 3, characterized in that, S6 comprises the following steps: S61. Establish a chassis temperature control scheme dataset F={f1,f2,…,f i ,…,f o }, where f i This represents the data for the i-th chassis temperature control scheme, and o represents the total number of chassis temperature control scheme data. S62, the white whale optimization algorithm is used to search the matching cabinet temperature regulation scheme data in the cabinet temperature regulation scheme data F and F, and the matching cabinet temperature regulation scheme data is marked and generated as the cabinet real-time temperature regulation scheme data F fangan .​​ 5. The intelligent regulation method for the case based on the Internet of Things according to claim 4, characterized in that, S62 comprises the following steps: S621, construct the control scheme search white whale population, set the population size N, the current iteration number t, the maximum iteration number t max And the chassis temperature control scheme data search space dimension P; Taking the case temperature regulation scheme data set as a case temperature regulation scheme data search space, randomly generating N case temperature regulation scheme data in the case temperature regulation scheme data search space, each case temperature regulation scheme data corresponding to a regulation scheme search white whale individual; S622, calculating the fitness value of each regulation scheme search white whale individual; S623, each regulatory regime searches for a white whale individual through a balancing factor controls its own swimming behavior in the chassis temperature regulatory regime data search space; If the balance factor is greater than 0.5, each regulatory scheme search white whale individual will take the mirror swimming strategy, through the method of swimming in the same direction with a randomly selected regulatory scheme search white whale individual in the cabinet temperature regulation scheme data search space to update the position; If the balance factor If the balance factor is less than or equal to 0.5, each control scheme search white whale individuals will share the prey location information, through the method of cooperative hunting optimal prey in the chassis temperature control scheme data search space position update; S624, updating the whale falling probability ω of the regulation scheme search white whale individual; S625, each regulation scheme search white whale individual performs a whale falling behavior to update the position in the case temperature regulation scheme data search space according to the whale falling probability ω; S626, calculating the fitness value of each regulation scheme search white whale individual after position updating, if the fitness value of the regulation scheme search white whale individual after position updating is greater than the fitness value of the original position, replacing the original position with the new position; otherwise, keeping the original position; Arranging each regulation scheme search white whale individual in descending order of fitness value, and selecting the regulation scheme search white whale individual with the highest fitness value as the current optimal individual; S627, judge whether t is less than t max , if t is less than t max , then t is added by 1, and return to S623; otherwise, the current optimal individual is taken as a global optimal solution, the chassis temperature regulation scheme data corresponding to the global optimal solution is outputted and data identified, and F fangan is generated. 6.The intelligent regulation method of the case based on the Internet of Things according to claim 5, characterized in that, S7 comprises the following steps: S71、will and F fangan Data combination is carried out to build the cabinet temperature regulation data ; S72, push to the cabinet temperature regulation platform through the communication network, and perform the cabinet temperature regulation operation. push to the cabinet temperature regulation platform through the communication network, and perform the cabinet temperature regulation operation.

7. An automatic temperature control case system for implementing the case intelligent regulation method based on the Internet of Things according to any one of claims 1-6.

Images