Cold chain equipment intelligent maintenance management method and system based on big data

Abstract

The invention relates to the technical field of cold chain equipment management, and discloses a cold chain equipment intelligent maintenance management method and system based on big data, and the system comprises a cold chain equipment refrigeration management module, a cold chain equipment refrigeration fault management module, and a cold chain equipment refrigeration maintenance module. A temperature sensor dynamically collects a real refrigeration operation temperature range value of the cold-chain equipment, and the real refrigeration operation temperature range value and a current optimal refrigeration temperature range value of the cold-chain equipment are subjected to precise judgment on a logic value relationship between a theoretical refrigeration temperature interval and an actual refrigeration temperature interval of the cold-chain equipment; intelligent detection of the numerical relationship between the actual refrigeration temperature and the theoretical refrigeration temperature of the cold chain equipment is realized; the cold chain equipment cold chain temperature adjustment fault state is accurately analyzed according to the cold chain equipment cold chain temperature interval numerical relationship judgment information, meanwhile, the cold chain equipment characteristic information is autonomously collected in cooperation with a cold chain equipment control center, the cold chain operation state of the cold chain equipment is intelligently monitored, and the reliability of cold chain maintenance management is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cold chain equipment management, in particular to a cold chain equipment intelligent maintenance management method and system based on big data. BACKGROUND

[0002] Cold chain equipment is the key to ensure the normal operation of cold chain logistics, such as refrigerated trucks, cold storage, refrigerated containers, etc. They can keep goods in a suitable low-temperature environment during transportation and storage, thereby ensuring product quality; for example, in fresh food distribution, if the refrigerated truck malfunctions, fresh vegetables and fruits may spoil, so attention must be paid to the maintenance of cold chain equipment. Regular maintenance and manual detection can effectively reduce the failure rate of cold chain equipment; the existing cold chain equipment cannot intelligently adjust the refrigeration temperature based on refrigerated goods during use, nor can it intelligently monitor refrigeration failures based on the refrigeration temperature adjustment state of the cold chain equipment, reducing the convenience and safety of cold chain equipment use.

[0003] The Chinese invention patent with publication number CN118586895B and publication date of 2024.11.05 discloses a device maintenance management system, which obtains device operation state monitoring records of a target device; identifies defects and faults of the target device based on the device operation state monitoring records, generates a fault alarm report; combines the fault alarm report with a device repair and maintenance account, implements target maintenance personnel to maintain the target device and generates a device maintenance record; dynamically adjusts a material procurement scheme based on the device maintenance record; realizes effective maintenance of the device while improving the timeliness of material supply; the above technical solution cannot intelligently maintain and manage equipment failures based on working condition scene types. SUMMARY

[0004] (I) Technical problems solved

[0005] To solve the above-mentioned problems that the existing cold chain equipment cannot intelligently adjust the refrigeration temperature based on refrigerated goods during use, nor can it intelligently monitor refrigeration failures based on the refrigeration temperature adjustment state of the cold chain equipment, reducing the convenience and safety of cold chain equipment use, and to achieve the purpose of autonomously obtaining refrigerated goods specification refrigeration information, intelligently evaluating the current optimal refrigeration temperature of the cold chain equipment, intelligently adjusting the refrigeration temperature of the cold chain equipment, real-time monitoring the refrigeration operating temperature range of the cold chain equipment, accurately analyzing the refrigeration failure state of the cold chain equipment, and efficiently performing cold chain equipment maintenance work.

[0006] (II) Technical solutions

[0007] The present application is implemented by the following technical solutions: a cold chain equipment intelligent maintenance management method based on big data, comprising the following steps:

[0008] S1, collect refrigerated goods refrigeration characteristic information;

[0009] S2, performing refrigerated product refrigeration temperature information extraction processing according to the refrigerated product refrigeration feature information, and generating a refrigerated product refrigeration temperature interval;

[0010] S3, performing optimal refrigeration temperature analysis processing of the current refrigerated product in the cold chain equipment based on the refrigerated product refrigeration temperature interval, and generating a current optimal refrigeration temperature interval of the cold chain equipment;

[0011] S4, performing cold chain equipment refrigeration temperature adjustment work according to the current optimal refrigeration temperature interval of the cold chain equipment, and collecting a cold chain equipment refrigeration running temperature interval;

[0012] S5, performing cold chain equipment theoretical and actual refrigeration temperature interval numerical relationship judgment processing based on the current optimal refrigeration temperature interval of the cold chain equipment and the cold chain equipment refrigeration running temperature interval, and generating cold chain equipment refrigeration temperature interval numerical relationship judgment information;

[0013] S6, performing cold chain equipment refrigeration fault state analysis processing according to the cold chain equipment refrigeration temperature interval numerical relationship judgment information, and generating cold chain equipment refrigeration fault state analysis information; when normal, continue to perform cold chain equipment refrigeration temperature adjustment work;

[0014] S7, when abnormal, collecting cold chain equipment feature information and constructing cold chain equipment refrigeration maintenance information, and then synchronously performing cold chain equipment refrigeration maintenance work.

[0015] Preferably, the operation steps of collecting refrigerated product refrigeration feature information are as follows:

[0016] S11, collecting product text information on the surface of the packaging bag of the refrigerated product to be refrigerated through an image scanner, and generating a refrigerated product refrigeration feature information set J = (j l ,…,j μ ), l = 1, 2, 3, …, μ; wherein j l represents refrigerated product refrigeration feature information corresponding to the lth refrigerated product type, and μ represents the maximum value of the number of refrigerated product types; the refrigerated product refrigeration feature information includes product name, product number, product standard refrigeration temperature range value, and refrigeration placement requirement information of the refrigerated product to be refrigerated.

[0017] Preferably, the operation steps of performing refrigerated product refrigeration temperature information extraction processing according to the refrigerated product refrigeration feature information, and generating a refrigerated product refrigeration temperature interval are as follows:

[0018] S21, using an LSA text search algorithm to search for refrigerated product refrigeration feature information j lThe standard refrigeration temperature text information search processing of the refrigeration goods according to the refrigeration goods type number order, the standard refrigeration temperature text information searched out is converted into temperature numerical interval data based on the Internet search platform, and the refrigeration goods refrigeration temperature interval set J'=(j'1,…,j' l ,…,j' μ ) is generated, wherein j' l represents the refrigeration goods refrigeration temperature interval corresponding to the lth refrigeration goods type; wherein j' l =[Φ l1 ,Φ l2 ], Φ l1 and Φ l2 respectively represent the refrigeration goods refrigeration minimum temperature value and the refrigeration goods refrigeration maximum temperature value in the refrigeration goods refrigeration temperature interval j' e , the values of Φ l1 and Φ l2 are both negative and the unit is degree Celsius; the Internet search platform includes any one of Baidu search platform, Sogou search platform and 360 search platform.

[0019] Preferably, the optimal refrigeration temperature analysis processing of the current refrigeration goods in the cold chain equipment based on the refrigeration goods refrigeration temperature interval is performed, and the operation steps for generating the current optimal refrigeration temperature interval of the cold chain equipment are as follows:

[0020] S31, obtaining the refrigeration goods refrigeration temperature interval set J';

[0021] S32, comparing the refrigeration goods refrigeration minimum temperature value Φ l and the refrigeration goods refrigeration maximum temperature value Φ l1 of the refrigeration goods refrigeration temperature interval j' l2 inside the refrigeration goods refrigeration temperature interval set J' according to the refrigeration temperature value size, searching out the refrigeration goods refrigeration temperature interval j' l corresponding to the minimum refrigeration temperature value, and constructing the current optimal refrigeration temperature interval K of the cold chain equipment, and the operation steps for constructing the current optimal refrigeration temperature interval K of the cold chain equipment are as follows:

[0022] S321, initialization: initializing r refrigeration temperature search particles in the search space of the refrigeration goods refrigeration temperature interval set J', and the refrigeration temperature search particles are initialized with the following attributes

[0023] The position of the n refrigeration temperature search particle: x n ,n=1,2,3,…,r;

[0024] The speed of the n refrigeration temperature search particle: v n ;

[0025] The optimal position that the nth refrigeration temperature search particle has passed through: pbest n ;

[0026] The optimal position that the whole refrigeration temperature search particle group has passed through: gbest n ;

[0027] The position limit of all refrigeration temperature search particles: x n ∈ [X min , X max ]; wherein X min and X max and respectively represent the position upper limit and the position lower limit of the refrigeration temperature search particle in the search space of the refrigeration item refrigeration temperature interval set J';

[0028] The speed limit of all refrigeration temperature search particles: v n ∈ [V min , V max ]; wherein V min and V max and respectively represent the speed upper limit and the speed lower limit of the refrigeration temperature search particle in the search space of the refrigeration item refrigeration temperature interval set J';

[0029] Set the maximum number of iterations △;

[0030] In each iteration process, set the self-learning factor Θ1 of the refrigeration temperature search particles in the search space of the refrigeration item refrigeration temperature interval set J', wherein Θ1 is used to adjust the degree of self-influence on the step length of each movement of the refrigeration temperature search particles in the search space of the refrigeration item refrigeration temperature interval set J';

[0031] In each iteration process, set the group learning factor Θ2 of the refrigeration temperature search particles in the search space of the refrigeration item refrigeration temperature interval set J', wherein Θ2 is used to adjust the degree of group influence on the step length of each movement of the refrigeration temperature search particles in the search space of the refrigeration item refrigeration temperature interval set J';

[0032] In each iteration process, set the inertia weight Ξ of the refrigeration temperature search particles in the search space of the refrigeration item refrigeration temperature interval set J'; wherein Ξ represents the ability of the search particles to inherit the speed at the previous time in the search space of the refrigeration item refrigeration temperature interval set J';

[0033] S322, calculate the fitness value of the refrigeration temperature search particle:

[0034] calculating the refrigerated article refrigeration temperature interval j' corresponding to the n-th refrigeration temperature search particle in the search space of the refrigerated article refrigeration temperature interval set J' l the refrigerated article refrigeration temperature interval j' corresponding to the target minimum refrigeration temperature value l a fitness value of the refrigerated article refrigeration temperature interval j'

[0035] S323, updating the refrigeration temperature search particle individual extreme value and the global optimal solution:

[0036] updating the optimal fitness value fpbest of the n-th refrigeration temperature search particle individual in the search space of the refrigerated article refrigeration temperature interval set J' n and the optimal fitness value fgbest of the refrigeration temperature search particle population as a whole n ; and then according to fpbest n updating the optimal position pbest of the refrigeration temperature search particle in the search space of the refrigerated article refrigeration temperature interval set J' n ; and then searching for the optimal position of the population from the optimal positions pbest n , and marking the optimal position gbest n as the global optimal position of this iteration;

[0037] S324, updating the speed and position of the refrigeration temperature search particle individual in the search space of the refrigerated article refrigeration temperature interval set J':

[0038] The update formula is as follows:

[0039] v' n = v n × Ξ + Θ1 × rand( ) × (pbest n - x n ) + Θ2 × rand( ) × (gbest n - x n ) ;

[0040] x' n = x n + v n ;

[0041] wherein v' n represents the n-th refrigeration temperature search particle searching for the refrigerated article refrigeration temperature interval j' corresponding to the target minimum refrigeration temperature value l updating the latest position after iteration in the search space of the refrigerated article refrigeration temperature interval set J'; x' n represents the n-th refrigeration temperature search particle searching for the refrigerated article refrigeration temperature interval j' corresponding to the target minimum refrigeration temperature value lupdating the latest speed after iteration in the search space of the refrigerated article refrigeration temperature interval set J'; rand() represents a random number function in the interval [0, 1];

[0042] If the position x n of the n-th refrigeration temperature search particle exceeds the boundary [X min ,X max ] during the iteration process, the x n of the refrigeration temperature search particle is adjusted to X min or X max ; if the speed v n of the n-th refrigeration temperature search particle exceeds the boundary [V min ,V max ], the v n of the refrigeration temperature search particle is adjusted to V min or V max ;

[0043] S325, setting a termination condition: when setting a maximum iteration number Δ, output the target minimum refrigeration temperature value corresponding to the refrigeration temperature interval j' e of the refrigeration article, and construct the current optimal refrigeration temperature interval K of the cold chain equipment, k1 and k2 respectively represent the current optimal refrigeration minimum temperature value and the current optimal refrigeration maximum temperature value of the cold chain equipment in the current optimal refrigeration temperature interval K of the cold chain equipment, and the values of k1 and k2 are both negative and in Celsius; the current optimal refrigeration temperature interval of the cold chain equipment represents the optimal temperature value interval meeting the refrigeration preservation requirements of all refrigeration articles in the cold chain equipment.

[0044] Preferably, the cold chain equipment refrigeration temperature adjustment operation is performed according to the current optimal refrigeration temperature interval of the cold chain equipment, and the operation steps of collecting the cold chain equipment refrigeration running temperature interval are as follows:

[0045] S41, controlling the cold chain equipment to perform refrigeration temperature adjustment operation on the refrigeration article according to the current optimal refrigeration minimum temperature value k1 and the current optimal refrigeration maximum temperature value k2 in the current optimal refrigeration temperature interval K of the cold chain equipment through the cold chain equipment control center;

[0046] S42, collecting the actual refrigeration temperature range value in the cold chain equipment refrigeration space during the execution of the cold chain equipment refrigeration temperature adjustment operation in step S41 through the temperature sensor, and generating the cold chain equipment refrigeration running temperature interval M = [m1, m2], wherein m1 and m2 respectively represent the cold chain equipment refrigeration running minimum temperature value and the cold chain equipment refrigeration running maximum temperature value in the cold chain equipment refrigeration running temperature M, and the values of m1 and m2 are both negative and in Celsius.

[0047] Preferably, the operation steps of generating the cold chain equipment refrigeration temperature interval numerical relationship judgment information based on the current optimal refrigeration temperature interval of the cold chain equipment, the refrigeration running temperature interval of the cold chain equipment, and the theoretical and actual refrigeration temperature interval numerical relationship judgment processing of the cold chain equipment are as follows:

[0048] S51, obtaining the current optimal refrigeration temperature interval K of the cold chain equipment and the refrigeration running temperature interval M of the cold chain equipment;

[0049] S52, comparing the current optimal refrigeration minimum temperature value k1 and the current optimal refrigeration maximum temperature value k2 in the current optimal refrigeration temperature interval K of the cold chain equipment with the refrigeration running minimum temperature value m1 and the refrigeration running maximum temperature value m2 in the refrigeration running temperature interval M of the cold chain equipment, and generating the cold chain equipment refrigeration temperature interval numerical relationship judgment information O according to the refrigeration temperature value comparison;

[0050] When m1≥k1 and m2≤k2, it indicates that the actual running temperature interval of the cold chain equipment conforms to the current optimal refrigeration temperature interval of the cold chain equipment, and the cold chain equipment refrigeration temperature interval numerical relationship judgment information O is output as M being equal to K or M being truly contained in K;

[0051] When m1<k1 and m2>k2, it indicates that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, and the cold chain equipment refrigeration temperature interval numerical relationship judgment information O is output as K being truly contained in M;

[0052] When m1<k2 and m2>k2, or m1<k1 and m2>k1, it indicates that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, and the cold chain equipment refrigeration temperature interval numerical relationship judgment information O is output as K intersecting with M;

[0053] When m1>k2 or m2<k1, it indicates that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, and the cold chain equipment refrigeration temperature interval numerical relationship judgment information O is output as K not intersecting with M.

[0054] Preferably, the refrigeration fault state analysis information of the cold chain equipment is generated according to the cold chain equipment refrigeration temperature interval numerical relationship judgment information, and when normal, the operation steps of continuing to perform the cold chain equipment refrigeration temperature adjustment operation are as follows:

[0055] S61, obtaining the cold chain equipment refrigeration temperature interval numerical relationship judgment information O;

[0056] S62, performing cold storage fault state analysis processing of the cold chain equipment based on the cold chain equipment cold storage temperature interval numerical relationship judgment information O, and generating cold chain equipment cold storage fault state analysis information L;

[0057] When the cold chain equipment cold storage temperature interval numerical relationship judgment information O is M equal to K and M is truly contained in K, it indicates that the actual running temperature of the cold chain equipment meets the cold chain equipment specification cold storage temperature requirement, and the cold chain equipment cold storage fault state analysis information L is output as normal. At this time, the cold chain equipment cold storage temperature adjustment operation is continued to be performed;

[0058] When the cold chain equipment cold storage temperature interval numerical relationship judgment information O is K truly contained in M, K intersects with M, and K does not intersect with M, it indicates that the actual running temperature of the cold chain equipment does not meet the cold chain equipment specification cold storage temperature requirement, and the cold chain equipment cold storage fault state analysis information L is output as abnormal.

[0059] Preferably, when the abnormality occurs, the operation steps of synchronously performing the cold chain equipment cold storage maintenance operation after collecting the cold chain equipment characteristic information and constructing the cold chain equipment cold storage maintenance information are as follows:

[0060] S71, when the cold chain equipment cold storage fault state analysis information L is abnormal, collecting the equipment identity characteristic information of the cold chain equipment performing the cold chain equipment cold storage temperature adjustment operation through the cold chain equipment control center online, and generating cold chain equipment characteristic information, wherein the cold chain equipment characteristic information includes product name, product model and use number information of the cold chain equipment;

[0061] S72, combining and identifying the data of the cold chain equipment cold storage fault state analysis information L and the cold chain equipment characteristic information to construct cold chain equipment cold storage maintenance information;

[0062] S73, pushing the cold chain equipment cold storage maintenance information to the cold chain equipment maintenance center through the Internet of Things communication network to notify the maintenance personnel to perform the cold chain equipment cold storage maintenance operation on the fault cold chain equipment.

[0063] A cold chain equipment intelligent maintenance management system based on big data is used to realize the cold chain equipment intelligent maintenance management method based on big data. The system includes a cold chain equipment cold storage management module, a cold chain equipment cold storage fault management module, and a cold chain equipment cold storage maintenance module.

[0064] The cold chain equipment cold storage management module includes a cold storage goods cold storage information collection unit, a cold storage goods cold storage temperature information extraction unit, and a cold chain equipment current optimal cold storage temperature analysis unit.

[0065] The refrigerated article refrigeration information acquisition unit acquires refrigerated article refrigeration characteristic information through an image scanner; the refrigerated article refrigeration temperature information extraction unit extracts refrigerated article refrigeration temperature information based on the refrigerated article refrigeration characteristic information and in combination with an Internet search platform, generates a refrigerated article refrigeration temperature interval; and the cold chain equipment current optimal refrigeration temperature analysis unit analyzes the optimal refrigeration temperature required by the current refrigerated article in the cold chain equipment based on the refrigerated article refrigeration temperature interval, generates a cold chain equipment current optimal refrigeration temperature interval.

[0066] The cold chain equipment refrigeration fault management module includes a cold chain equipment refrigeration temperature adjustment unit, a cold chain equipment refrigeration running temperature acquisition unit, a cold chain equipment refrigeration temperature numerical relationship judgment unit, a cold chain equipment refrigeration fault state analysis unit, and a cold chain equipment characteristic information acquisition unit.

[0067] The cold chain equipment refrigeration temperature adjustment unit adjusts the refrigeration temperature of the cold chain equipment based on the cold chain equipment current optimal refrigeration temperature interval and in combination with a cold chain equipment control center; the cold chain equipment refrigeration running temperature acquisition unit acquires a cold chain equipment refrigeration running temperature interval through a temperature sensor; the cold chain equipment refrigeration temperature numerical relationship judgment unit judges the numerical relationship between the theoretical and actual refrigeration temperature intervals of the cold chain equipment based on the cold chain equipment current optimal refrigeration temperature interval and the cold chain equipment refrigeration running temperature interval, generates cold chain equipment refrigeration temperature interval numerical relationship judgment information; the cold chain equipment refrigeration fault state analysis unit analyzes the refrigeration fault state of the cold chain equipment based on the cold chain equipment refrigeration temperature interval numerical relationship judgment information, generates cold chain equipment refrigeration fault state analysis information; and the cold chain equipment characteristic information acquisition unit acquires cold chain equipment characteristic information through a cold chain equipment control center.

[0068] The cold chain equipment refrigeration maintenance module includes a cold chain equipment refrigeration maintenance information construction unit and a cold chain equipment refrigeration maintenance operation execution unit.

[0069] The cold chain equipment refrigeration maintenance information construction unit constructs cold chain equipment refrigeration maintenance information based on cold chain equipment refrigeration fault state analysis information and cold chain equipment characteristic information; and the cold chain equipment refrigeration maintenance operation execution unit executes cold chain equipment refrigeration maintenance operations based on the cold chain equipment refrigeration maintenance information in combination with a cold chain equipment maintenance center.

[0070] (Three) Beneficial Effects

[0071] The present application provides a cold chain equipment intelligent maintenance management method and system based on big data. The following beneficial effects are achieved:

[0072] One, the cold chain equipment intelligent maintenance management system provided by the application realizes intelligent acquisition of standard cold storage temperature information of cold chain equipment based on big data, intelligent evaluation of optimal cold storage temperature of cold chain equipment based on cold storage temperature interval of cold chain equipment and intelligent setting of optimal cold storage temperature range value of cold chain equipment based on cold chain equipment object.

[0073] Two, the cold chain equipment intelligent maintenance management system provided by the application realizes safe and reliable adjustment of cold chain equipment cold storage temperature based on cold chain equipment current optimal cold storage temperature interval information, intelligent detection of actual cold storage temperature and theoretical cold storage temperature numerical relationship of cold chain equipment based on dynamic acquisition of cold chain equipment cold storage real running temperature range value by a temperature sensor and accurate judgment of logical numerical relationship between cold chain equipment theoretical cold storage temperature interval and actual cold storage temperature interval, and accurate analysis of cold chain equipment cold storage temperature adjustment fault state based on cold chain equipment cold storage temperature interval numerical relationship judgment information.

[0074] Three, the cold chain equipment intelligent maintenance management system provided by the application realizes scientific and comprehensive detection of cold chain equipment cold storage control fault and autonomous acquisition of fault cold chain equipment object information based on cold chain equipment cold storage fault state analysis information and cold chain equipment characteristic information, realizes intelligent supervision of cold chain equipment cold chain running state, and improves the reliability of cold chain maintenance management. BRIEF DESCRIPTION OF DRAWINGS

[0075] Figure 1 A module schematic diagram of the cold chain equipment intelligent maintenance management system based on big data provided by the application;

[0076] Figure 2 A flowchart of the cold chain equipment intelligent maintenance management method based on big data provided by the application. DETAILED DESCRIPTION

[0077] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0078] The implementation of the cold chain equipment intelligent maintenance management method and system based on big data is as follows:

[0079] Embodiment 1

[0080] Please refer to Figure 1 - Figure 2 A cold chain equipment intelligent maintenance management method based on big data, the method comprising the following steps:

[0081] S1, collecting cold storage characteristic information of cold storage goods;

[0082] S2, extracting and processing cold storage temperature information of cold storage goods according to the cold storage characteristic information of cold storage goods, and generating a cold storage temperature interval of cold storage goods;

[0083] S3, analyzing and processing the optimal cold storage temperature required by the current cold storage goods in the cold chain equipment based on the cold storage temperature interval of the cold storage goods, and generating a current optimal cold storage temperature interval of the cold chain equipment;

[0084] S4, performing cold storage temperature adjustment work of the cold chain equipment according to the current optimal cold storage temperature interval of the cold chain equipment, and collecting a cold storage running temperature interval of the cold chain equipment;

[0085] S5, judging the numerical relationship between the theoretical and actual cold storage temperature intervals of the cold chain equipment based on the current optimal cold storage temperature interval of the cold chain equipment and the cold storage running temperature interval of the cold chain equipment, and generating cold storage temperature interval numerical relationship judgment information of the cold chain equipment;

[0086] S6, analyzing and processing the cold storage fault state of the cold chain equipment according to the cold storage temperature interval numerical relationship judgment information of the cold chain equipment, and generating cold storage fault state analysis information of the cold chain equipment; when normal, continue to perform cold storage temperature adjustment work of the cold chain equipment;

[0087] S7, when abnormal, collecting cold chain equipment characteristic information and constructing cold storage maintenance information of the cold chain equipment, and then synchronously performing cold storage maintenance work of the cold chain equipment.

[0088] Further, please refer to Figure 1 - Figure 2 The operation steps of collecting cold storage characteristic information of cold storage goods are as follows:

[0089] S11, collecting product text information on the surface of the packaging bag of the refrigerated goods to be refrigerated through an image scanner online, and generating a refrigerated goods refrigeration feature information set J=(j1,…,j l ,…,j μ ), l=1, 2, 3,…, μ; wherein j l represents the refrigerated goods refrigeration feature information corresponding to the lth refrigerated goods type, and μ represents the maximum value of the number of refrigerated goods types; the refrigerated goods refrigeration feature information includes the product name, product number, product standard refrigeration temperature range value, and refrigeration placement requirement information of the refrigerated goods to be refrigerated.

[0090] The operation steps for extracting refrigerated goods refrigeration temperature information according to the refrigerated goods refrigeration feature information to generate a refrigerated goods refrigeration temperature interval are as follows:

[0091] S21, using an LSA text search algorithm to search for refrigerated goods standard refrigeration temperature text information in the refrigerated goods refrigeration feature information set J based on refrigeration temperature keywords, and converting the searched refrigerated goods standard refrigeration temperature text information into temperature value interval data based on an Internet search platform, and generating a refrigerated goods refrigeration temperature interval set J'=(j'1,…,j' l The operation steps for extracting refrigerated goods refrigeration temperature information according to the refrigerated goods refrigeration feature information to generate a refrigerated goods refrigeration temperature interval are as follows:

[0091] S21, using an LSA text search algorithm to search for refrigerated goods standard refrigeration temperature text information in the refrigerated goods refrigeration feature information set J based on refrigeration temperature keywords, and converting the searched refrigerated goods standard refrigeration temperature text information into temperature value interval data based on an Internet search platform, and generating a refrigerated goods refrigeration temperature interval set J'=(j'1,…,j' l ,…,j' μ ), wherein j' l represents the refrigerated goods refrigeration temperature interval corresponding to the lth refrigerated goods type; wherein j' l =[Φ l1 ,Φ l2 ], Φ l1 and Φ l2 represent the refrigerated goods refrigeration minimum temperature value and the refrigerated goods refrigeration maximum temperature value in the refrigerated goods refrigeration temperature interval j' l , respectively, and the values of Φ l1 and Φ l2 are both negative and in degrees Celsius; the Internet search platform includes any one of the Baidu search platform, the Sogou search platform, and the 360 search platform.

[0092] The operation steps for analyzing and processing the optimal refrigeration temperature required for the current refrigerated goods in the cold chain equipment based on the refrigerated goods refrigeration temperature interval to generate the current optimal refrigeration temperature interval of the cold chain equipment are as follows:

[0093] S31, obtaining the refrigerated goods refrigeration temperature interval set J';

[0094] S32, the refrigerated goods refrigeration minimum temperature value Φ l of the refrigerated goods refrigeration temperature interval j' l1Maximum refrigeration temperature value Φ for refrigerated items l2 The refrigeration temperature values ​​are compared sequentially according to the type number of the refrigerated items to find the refrigeration temperature range j' corresponding to the smallest refrigeration temperature value. l The optimal refrigeration temperature range K for the current cold chain equipment is determined. The steps for determining the optimal refrigeration temperature range K for the current cold chain equipment are as follows:

[0095] S321. Initialization: In the search space of the refrigeration temperature range set J' of refrigerated items, initialize r refrigeration temperature search particles. The refrigeration temperature search particles are initialized with the following attributes respectively.

[0096] The position of the particle searched at the nth refrigeration temperature: x n n = 1, 2, 3, ..., r;

[0097] The velocity of the particle searching at the nth refrigeration temperature: v n ;

[0098] The optimal position traversed by the particle at the nth refrigeration temperature: pbest n ;

[0099] The optimal location traversed by the particle swarm throughout the entire refrigeration temperature search: gbest n ;

[0100] Add an upper limit to the position of all search particles at refrigerated temperatures: x n ∈[X min ,X max ]; where X min and X max and represent the upper and lower boundaries of the position of the refrigeration temperature search particle in the search space of the refrigeration temperature range set J' of refrigerated items, respectively;

[0101] Add a speed limit to the search particles at all refrigerated temperatures: v n ∈[V min V max ]; where V min and V max and represent the upper and lower bounds of the velocity of the particle being searched in the search space of the refrigerated item refrigeration temperature range set J', respectively;

[0102] Set the maximum number of iterations △;

[0103] In each iteration, a self-learning factor Θ1 is set for the refrigeration temperature search particles in the search space of the refrigeration temperature range set J' of refrigerated items. Θ1 is used to adjust the degree to which the step size of each movement of the refrigeration temperature search particles in the search space of the refrigeration temperature range set J' of refrigerated items is affected by the self.

[0104] In each iteration, a population learning factor Θ2 is set for the refrigeration temperature search particles in the search space of the refrigeration temperature range set J' of refrigerated items. Θ2 is used to adjust the degree to which the step size of each movement of the refrigeration temperature search particles in the search space of the refrigeration temperature range set J' of refrigerated items is affected by the population.

[0105] In each iteration, the inertial weight Ξ of the refrigeration temperature search particles in the search space of the refrigeration temperature range set J' of refrigerated items is set; where Ξ represents the ability of the search particles to inherit the velocity of the previous moment in the search space of the refrigeration temperature range set J' of refrigerated items.

[0106] S322. Calculate the fitness value of the search particle at the refrigeration temperature:

[0107] Calculate the refrigeration temperature range j' corresponding to the nth refrigeration temperature search particle in the search space of the refrigeration temperature range set J' of refrigerated items. l The refrigeration temperature range j' of refrigerated items corresponding to the target minimum refrigeration temperature value l fitness value;

[0108] S323. Update the individual extreme values ​​and global optimal solution for searching the refrigeration temperature particle:

[0109] Update the optimal fitness value fpbest of the nth individual refrigeration temperature search particle in the search space of the refrigeration temperature range set J' for refrigerated items. n The optimal fitness value fgbest for the entire particle population is determined by the refrigeration temperature. n ; and then according to fpbest n Update the optimal position pbest of the refrigeration temperature search particle in the search space of the refrigeration temperature range set J' for refrigerated items. n Then from these optimal positions, pbest n The optimal position of a group is found by searching in gbest. n And the optimal position gbest n This is marked as the globally optimal position in this iteration;

[0110] S324. Update the velocity and position of the individual particle in the search space of the refrigeration temperature range set J' of refrigerated items:

[0111] The updated formula is as follows:

[0112] v' n =v n ×Ξ+Θ1×rand( )×(pbest n -x n )+Θ2×rand()×(gbest n -xn );

[0113] x’ n =x n +v n ;

[0114] wherein v’ n represents the j'th refrigerated temperature interval searched by then'th refrigerated temperature search particle l updating the latest position after iteration in the search space of the refrigerated temperature interval set J'; x' n represents the j'th refrigerated temperature interval searched by then'th refrigerated temperature search particle l updating the latest speed after iteration in the search space of the refrigerated temperature interval set J'; rand() represents a random number function in the interval [0, 1];

[0115] If, in the iteration process, the position x n of then'th refrigerated temperature search particle exceeds the boundary [X min , X max ], the x n of the refrigerated temperature search particle is adjusted to X min or X max ; if the speed v n of then'th refrigerated temperature search particle exceeds the boundary [V min , V max ], the v n of the refrigerated temperature search particle is adjusted to V min or V max ;

[0116] S325, setting a termination condition: when setting a maximum iteration number △, output the j'th refrigerated temperature interval corresponding to the target minimum refrigerated temperature value l , and construct the current optimal refrigerated temperature interval K of the cold chain equipment, k1 and k2 respectively represent the current optimal refrigerated minimum temperature value and the current optimal refrigerated maximum temperature value in the current optimal refrigerated temperature interval K of the cold chain equipment, the values of k1 and k2 are both negative and the unit is Celsius degree; the current optimal refrigerated temperature interval of the cold chain equipment represents the optimal temperature value interval meeting the refrigerated storage requirements of all refrigerated goods in the cold chain equipment.

[0117] The refrigerated article refrigeration information acquisition unit and the refrigerated article refrigeration temperature information extraction unit cooperate with each other, the image scanner is used to dynamically acquire the refrigerated article refrigeration characteristic information, and the intelligent search algorithm and the Internet search platform are used to accurately and reliably extract the refrigeration temperature information of the refrigerated article placed in the cold chain equipment, so that the standard refrigeration temperature information of the refrigerated article in the cold chain equipment is intelligently collected based on big data; the cold chain equipment current optimal refrigeration temperature analysis unit intelligently evaluates the optimal refrigeration temperature in the cold chain equipment that meets the refrigeration standard requirements of all refrigerated articles based on the refrigeration temperature interval of the refrigerated article and in combination with the intelligent recognition algorithm, so that the current optimal refrigeration temperature range value of the cold chain equipment is intelligently set based on the refrigeration object of the cold chain equipment, and the intelligence and applicability of the refrigeration management of the cold chain equipment are improved.

[0118] Further, please refer to Figure 1 Figure 2 According to the current optimal refrigeration temperature interval of the cold chain equipment, the refrigeration temperature adjustment operation of the cold chain equipment is performed, and the operation steps of collecting the refrigeration running temperature interval of the cold chain equipment are as follows:

[0119] S41, the cold chain equipment control center controls the cold chain equipment to perform the refrigeration temperature adjustment operation on the refrigerated article according to the current optimal refrigeration minimum temperature value k1 and the current optimal refrigeration maximum temperature value k2 in the current optimal refrigeration temperature interval K of the cold chain equipment;

[0120] S42, the actual refrigeration temperature range value in the refrigeration space of the cold chain equipment during the refrigeration temperature adjustment operation of the cold chain equipment in step S41 is collected online by the temperature sensor, and the refrigeration running temperature interval M = [m1, m2] of the cold chain equipment is generated, wherein m1 and m2 respectively represent the refrigeration running minimum temperature value and the refrigeration running maximum temperature value of the cold chain equipment in the refrigeration running temperature M of the cold chain equipment, and m1 and m2 are both negative and in Celsius.

[0121] Based on the current optimal refrigeration temperature interval of the cold chain equipment and the refrigeration running temperature interval of the cold chain equipment, the operation steps of generating the refrigeration temperature interval numerical relationship judgment information of the cold chain equipment are as follows:

[0122] S51, the current optimal refrigeration temperature interval K of the cold chain equipment and the refrigeration running temperature interval M of the cold chain equipment are obtained;

[0123] ​S52, respectively compare the cold chain equipment current optimal refrigeration minimum temperature value k1 and the cold chain equipment current optimal refrigeration maximum temperature value k2 in the cold chain equipment current optimal refrigeration temperature interval K with the cold chain equipment refrigeration running minimum temperature value m1 and the cold chain equipment refrigeration running maximum temperature value m2 in the cold chain equipment refrigeration running temperature interval M, and generate cold chain equipment refrigeration temperature interval value relationship judgment information O according to the refrigeration temperature value comparison;

[0124] When m1≥k1 and m2≤k2, it means that the actual running temperature interval of the cold chain equipment conforms to the current optimal refrigeration temperature interval of the cold chain equipment, so the cold chain equipment refrigeration temperature interval value relationship judgment information O is output as M is equal to K or M is truly contained in K;

[0125] When m1<k1 and m2>k2, it means that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, so the cold chain equipment refrigeration temperature interval value relationship judgment information O is output as K is truly contained in M;

[0126] When m1<k2 and m2>k2, or m1<k1 and m2>k1, it means that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, so the cold chain equipment refrigeration temperature interval value relationship judgment information O is output as K intersects with M;

[0127] When m1>k2 or m2<k1, it means that the actual running temperature interval of the cold chain equipment does not conform to the current optimal refrigeration temperature interval of the cold chain equipment, so the cold chain equipment refrigeration temperature interval value relationship judgment information O is output as K does not intersect with M.

[0128] According to the cold chain equipment refrigeration temperature interval value relationship judgment information, analyze and process the refrigeration fault state of the cold chain equipment, and generate cold chain equipment refrigeration fault state analysis information. When normal, continue to execute the operation steps of the cold chain equipment refrigeration temperature adjustment job as follows:

[0129] S61, obtain the cold chain equipment refrigeration temperature interval value relationship judgment information O;

[0130] S62, based on the cold chain equipment refrigeration temperature interval value relationship judgment information O, analyze and process the refrigeration fault state of the cold chain equipment, and generate cold chain equipment refrigeration fault state analysis information L;

[0131] When the cold chain equipment refrigeration temperature interval value relationship judgment information O is M equal to K and M truly contained in K, it means that the actual running temperature of the cold chain equipment conforms to the specification refrigeration temperature requirement of the cold chain equipment, so the cold chain equipment refrigeration fault state analysis information L is output as normal, and at this time the cold chain equipment refrigeration temperature adjustment job is continued to be executed;

[0132] When the cold chain equipment refrigeration temperature interval numerical relationship judgment information O is K true contained in M, K intersects with M and K does not intersect with M, it indicates that the actual operation temperature of the cold chain equipment does not meet the specification refrigeration temperature requirement of the cold chain equipment, and then the cold chain equipment refrigeration fault state analysis information L is output as abnormal.

[0133] Through the cold chain equipment refrigeration temperature adjustment unit, the cold chain equipment refrigeration temperature adjustment operation is independently and accurately performed by the cold chain equipment control center according to the current optimal refrigeration temperature interval information of the cold chain equipment, so as to realize safe and reliable adjustment of the refrigeration temperature of the cold chain equipment based on refrigerated goods; the cold chain equipment refrigeration running temperature acquisition unit and the cold chain equipment refrigeration temperature numerical relationship judgment unit cooperate with each other, the real running temperature range value of the cold chain equipment refrigeration is dynamically collected by the temperature sensor, and the cold chain equipment theoretical refrigeration temperature interval and the actual refrigeration temperature interval are accurately judged by comparing with the current optimal refrigeration temperature range value of the cold chain equipment, so as to realize intelligent detection of the numerical relationship between the actual refrigeration temperature and the theoretical refrigeration temperature of the cold chain equipment, and improve the accuracy of the refrigeration management of the cold chain equipment; the cold chain equipment refrigeration fault state analysis unit and the cold chain equipment feature information acquisition unit cooperate with each other, the cold chain equipment refrigeration temperature adjustment fault state is accurately analyzed according to the cold chain equipment refrigeration temperature interval numerical relationship judgment information, and at the same time, the cold chain equipment feature information is independently collected by the cold chain equipment control center, so as to realize scientific and comprehensive detection of the refrigeration control fault of the cold chain equipment and independent acquisition of the object information of the fault cold chain equipment, realize intelligent supervision of the cold chain operation state of the cold chain equipment, and improve the reliability of the cold chain maintenance management.

[0134] Further, please refer to Figure 1 - Figure 2 When the abnormality occurs, the operation steps of collecting the cold chain equipment feature information and constructing the cold chain equipment refrigeration maintenance information and then synchronously performing the cold chain equipment refrigeration maintenance operation are as follows:

[0135] S71, when the cold chain equipment refrigeration fault state analysis information L is abnormal, the equipment identity feature information of the cold chain equipment performing the cold chain equipment refrigeration temperature adjustment operation is collected online by the cold chain equipment control center, and the cold chain equipment feature information is generated, which includes the product name, product model and use number information of the cold chain equipment;

[0136] S72, the cold chain equipment refrigeration fault state analysis information L and the cold chain equipment feature information are combined and identified to construct the cold chain equipment refrigeration maintenance information.

[0137] S73, the cold chain equipment refrigeration maintenance information is pushed to the cold chain equipment maintenance center through the Internet of Things communication network to notify the maintenance personnel to perform the cold chain equipment refrigeration maintenance operation on the fault cold chain equipment.

[0138] The cold chain equipment refrigeration maintenance information construction unit autonomously and scientifically constructs cold chain equipment refrigeration maintenance information based on cold chain equipment refrigeration fault state analysis information and cold chain equipment feature information, so as to realize timely and accurate acquisition of cold chain equipment refrigeration maintenance information; the cold chain equipment refrigeration maintenance operation execution unit accurately and reliably executes cold chain equipment refrigeration maintenance operations according to the cold chain equipment refrigeration maintenance information in combination with the cold chain equipment maintenance center, so as to realize accurate emergency response to cold chain equipment refrigeration abnormalities and improve the scientific nature and safety of cold chain equipment supervision.

[0139] Embodiment 2:

[0140] Please refer to Figure 1 - Figure 2 A cold chain equipment intelligent maintenance management system based on big data is used to realize a cold chain equipment intelligent maintenance management method based on big data. The system includes a cold chain equipment refrigeration management module, a cold chain equipment refrigeration fault management module, and a cold chain equipment refrigeration maintenance module.

[0141] The cold chain equipment refrigeration management module includes a refrigerated goods refrigeration information acquisition unit, a refrigerated goods refrigeration temperature information extraction unit, and a cold chain equipment current optimal refrigeration temperature analysis unit.

[0142] The refrigerated goods refrigeration information acquisition unit acquires refrigerated goods refrigeration feature information through an image scanner. The refrigerated goods refrigeration temperature information extraction unit extracts refrigerated goods refrigeration temperature information according to refrigerated goods refrigeration feature information in combination with an Internet search platform to generate a refrigerated goods refrigeration temperature interval. The cold chain equipment current optimal refrigeration temperature analysis unit analyzes and processes the optimal refrigeration temperature required for the current refrigerated goods in the cold chain equipment based on the refrigerated goods refrigeration temperature interval to generate a cold chain equipment current optimal refrigeration temperature interval.

[0143] The cold chain equipment refrigeration fault management module includes a cold chain equipment refrigeration temperature adjustment unit, a cold chain equipment refrigeration running temperature acquisition unit, a cold chain equipment refrigeration temperature numerical relationship judgment unit, a cold chain equipment refrigeration fault state analysis unit, and a cold chain equipment feature information acquisition unit.

[0144] The cold chain equipment refrigeration temperature adjustment unit performs a cold chain equipment refrigeration temperature adjustment operation according to a current optimal refrigeration temperature interval of the cold chain equipment and in combination with a cold chain equipment control center; the cold chain equipment refrigeration running temperature collection unit collects a cold chain equipment refrigeration running temperature interval through a temperature sensor; the cold chain equipment refrigeration temperature value relationship judgment unit performs a cold chain equipment theoretical and actual refrigeration temperature interval value relationship judgment process based on the current optimal refrigeration temperature interval of the cold chain equipment and the cold chain equipment refrigeration running temperature interval, and generates cold chain equipment refrigeration temperature interval value relationship judgment information; the cold chain equipment refrigeration fault state analysis unit performs a cold chain equipment refrigeration fault state analysis process according to the cold chain equipment refrigeration temperature interval value relationship judgment information, and generates cold chain equipment refrigeration fault state analysis information; and the cold chain equipment characteristic information collection unit collects cold chain equipment characteristic information through the cold chain equipment control center.

[0145] The cold chain equipment refrigeration maintenance module includes a cold chain equipment refrigeration maintenance information construction unit and a cold chain equipment refrigeration maintenance operation execution unit.

[0146] The cold chain equipment refrigeration maintenance information construction unit constructs cold chain equipment refrigeration maintenance information based on the cold chain equipment refrigeration fault state analysis information and the cold chain equipment characteristic information; and the cold chain equipment refrigeration maintenance operation execution unit executes a cold chain equipment refrigeration maintenance operation according to the cold chain equipment refrigeration maintenance information in combination with a cold chain equipment maintenance center.

[0147] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A big data-based cold chain equipment intelligent maintenance management method, characterized in that, The method comprises the following steps: S1, collecting cold storage characteristic information of the cold storage goods; S2, extracting cold storage temperature information of the cold storage goods according to the cold storage characteristic information of the cold storage goods, and generating a cold storage temperature interval of the cold storage goods; S3, analyzing and processing the optimal cold storage temperature required by the current cold storage goods in the cold chain equipment based on the cold storage temperature interval of the cold storage goods, and generating a current optimal cold storage temperature interval of the cold chain equipment; S4, performing a cold storage temperature adjustment operation of the cold chain equipment according to the current optimal cold storage temperature interval of the cold chain equipment, and collecting a cold storage running temperature interval of the cold chain equipment; S5, judging the numerical relationship between the theoretical and actual cold storage temperature intervals of the cold chain equipment based on the current optimal cold storage temperature interval of the cold chain equipment and the cold storage running temperature interval of the cold chain equipment, and generating cold storage temperature interval numerical relationship judgment information of the cold chain equipment; S6, analyzing the cold storage fault state of the cold chain equipment according to the cold storage temperature interval numerical relationship judgment information of the cold chain equipment, and generating cold storage fault state analysis information of the cold chain equipment; when normal, continue to perform the cold storage temperature adjustment operation of the cold chain equipment; S7, when abnormal, collect the characteristic information of the cold chain equipment and construct cold storage maintenance information of the cold chain equipment, and then synchronously perform a cold storage maintenance operation of the cold chain equipment.

2. The method for intelligent maintenance management of cold chain equipment based on big data according to claim 1, characterized in that: The S1 comprises the following steps: S11, collecting the product text information on the surface of the packaging bag of the refrigerated goods to be scanned by an image scanner online, and generating a set of refrigerated goods refrigeration feature information J, wherein J includes j l ; wherein j l represents the refrigerated goods refrigeration feature information corresponding to the lth refrigerated goods type.

3. The method of claim 2, wherein: The S2 comprises the following steps: S21, based on the refrigeration temperature keyword, using the LSA text search algorithm to search the j in the J l The standard refrigeration temperature text information search process of the refrigeration goods according to the refrigeration goods type number order, the searched refrigeration goods standard refrigeration temperature text information is converted into temperature numerical interval data based on the Internet search platform, and a refrigeration goods refrigeration temperature interval set J' is generated, the J' includes j' l ; Wherein j' l represents the refrigeration temperature interval of the lth refrigeration goods type; Wherein j' l =[Φ l1 ,Φ l2 ], Φ l1 and Φ l2 respectively represent the refrigeration minimum temperature value and the refrigeration maximum temperature value of the refrigeration goods in the refrigeration temperature interval j' l ; The value of Φ l1 and Φ l2 is negative and the unit is Celsius.

4. The method of claim 3, wherein: The S3 comprises the following steps: S31, obtaining the J'; S32, the j' inside the J' is compared with the j' inside the J' l the Φ of the J' l1 and the Φ l2 According to the refrigeration temperature value size comparison of the refrigeration article type number order, the smallest refrigeration temperature value corresponding to the j' is searched out l , and the current optimal refrigeration temperature interval K of the cold chain equipment is constructed. The operation steps of constructing the current optimal refrigeration temperature interval K of the cold chain equipment are as follows: S321, initialization: initializing r cold storage temperature search particles in the search space of the J', and initializing the following attributes of the cold storage temperature search particles respectively The position of the nth refrigeration temperature search particle: x n n = 1, 2, 3, …, r; Speed of the nth refrigeration temperature search particle: v n ; Optimal position passed by the nth refrigeration temperature search particle: pbest n ; The optimal position that the whole refrigeration temperature search particle swarm has gone through: gbest n ; Add limits to the position of the cold temperature search particle: x n ∈ [X min , X max ] ; where X min and X max represent the upper and lower bounds on the position of the cold temperature search particle in the search space of the J'. Add a restriction to the velocity of all cold temperature search particles: v n ∈ [V min , V max ] ; where V min and V max represent the upper and lower bounds on the velocity of the cold temperature search particles in the search space of the J' ; setting the maximum number of iterations △; in each iteration process, setting the self-learning factor Θ1 of the cold storage temperature search particles in the search space of the J'; in each iteration process, setting the group learning factor Θ2 of the cold storage temperature search particles in the search space of the J'; in each iteration process, setting the inertia weight Ξ of the cold storage temperature search particles in the search space of the J'; S322, calculating the fitness value of the cold storage temperature search particle: calculating the j' corresponding to the n-th refrigeration temperature search particle in the search space of the J' l the j' corresponding to the target minimum refrigeration temperature value l the fitness value of the J S323, updating the individual extreme value and the global optimal solution of the cold storage temperature search particle: Update the optimal fitness value fpbest of the nth cold storage temperature search particle in the search space of Jv. n The optimal fitness value fgbest for the entire particle population is determined by the refrigeration temperature. n ; and then according to fpbest n Update the optimal position pbest of the refrigeration temperature search particle in the search space of J′. n Then from these optimal positions, pbest n The optimal position of a group is found by searching in the middle, and the optimal position is set as gbest. n This is marked as the globally optimal position in this iteration; S324, updating the speed and position of the cold storage temperature search particle in the search space of the J'; If, during the iteration process, the position x of the search particle at the nth refrigeration temperature... n If the boundary is exceeded, then the x-value of the search particle at that refrigeration temperature is... n Adjusted to X min or X max The velocity v of the particle being searched at the nth refrigeration temperature n Exceeding the boundary [V] min V max ], then the refrigeration temperature is used to search for the particle's v n Adjusted to V min or V max ; S325, set the termination condition: when setting the maximum iteration number Δ, output the j l And the current optimal refrigeration temperature interval K of the cold chain equipment is constructed, k1 and k2 respectively represent the current optimal refrigeration minimum temperature value and the current optimal refrigeration maximum temperature value in the current optimal refrigeration temperature interval K of the cold chain equipment, the values of k1 and k2 are both negative and the unit is Celsius degree.

5. The method for intelligent maintenance management of cold chain equipment based on big data according to claim 4, characterized in that: The S4 comprises the following steps: S41, performing a cold storage temperature adjustment operation of the cold chain equipment on the cold storage goods by the cold chain equipment control center according to the k1 and the k2 in the K; S42, collecting the actual cold storage temperature range value in the cold chain equipment cold storage space during the cold storage temperature adjustment operation of the cold chain equipment in step S41 by the temperature sensor, and generating a cold storage running temperature interval M=[m1, m2] of the cold chain equipment, wherein m1 and m2 respectively represent the minimum cold storage running temperature value and the maximum cold storage running temperature value of the cold chain equipment in the M, and the values of m1 and m2 are both negative and in Celsius.

6. The method of claim 5, wherein: The S5 comprises the following steps: S51, obtaining the K and the M; S52, respectively, the k1 and the k2 in the K and the m1 and the m2 in the M are compared in terms of cold storage temperature value size, and cold chain equipment cold storage temperature interval value relationship judgment information O is generated according to the comparison of the cold storage temperature value size; When m1≥k1 and m2≤k2, the O is output as M being equal to K or M being truly contained in K; When m1<k1 and m2>k2, the O is output as K being truly contained in M; When m1<k2 and m2>k2, or m1<k1 and m2>k1, the O is output as K intersecting with M; When m1>k2 or m2<k1, the O is output as K not intersecting with M.

7. The method of claim 6, wherein: The S6 comprises the following steps: S61, the O is acquired; S62, cold chain equipment cold storage fault state analysis processing is performed based on the O, and cold chain equipment cold storage fault state analysis information L is generated; When the O is M being equal to K and M being truly contained in K, the L is output as normal, and cold chain equipment cold storage temperature adjustment operation is continued to be performed; When the O is K being truly contained in M, K intersecting with M, and K not intersecting with M, the L is output as abnormal.

8. The method of claim 7, wherein: The S7 comprises the following steps: S71, when the L is abnormal, equipment identity feature information of cold chain equipment performing cold chain equipment cold storage temperature adjustment operation is collected online by a cold chain equipment control center, and cold chain equipment feature information is generated; S72, the L and the cold chain equipment feature information are combined and identified to construct cold chain equipment cold storage maintenance information; S73, the cold chain equipment cold storage maintenance information is pushed to a cold chain equipment maintenance center through an Internet of Things communication network to notify maintenance personnel to perform cold chain equipment cold storage maintenance operation on the fault cold chain equipment. 9.A big data based intelligent maintenance management system for cold chain equipment, configured to implement the big data based intelligent maintenance management method for cold chain equipment according to any one of claims 1-8. The system comprises a cold chain equipment cold storage management module, a cold chain equipment cold storage fault management module, and a cold chain equipment cold storage maintenance module.

Images