Remote fault monitoring and processing method of unmanned automatic car washing equipment and storage medium

Abstract

The invention discloses a remote fault monitoring processing method of unmanned automatic car washing equipment and a storage medium, and relates to the technical field of fault monitoring, the processing method comprises the following steps: carrying out link division on data stored in any car washing record; randomly selecting one car washing record, and evaluating each link to obtain the comprehensive completion degree and the actual completion degree of the car washing record; performing difference analysis on evaluation results of all links through difference comparison of the completeness; analyzing the correlation degree between any two adjacent links according to the data corresponding to each link; performing abnormity judgment on each link in the car washing record based on the correlation degree between the links; setting a risk judgment condition of each link based on the generation condition of each risk link; and evaluating a real-time car washing record newly generated on the car washing data management platform, and judging whether risk early warning is performed on the real-time car washing record or not.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and in particular to a remote fault monitoring processing method and a storage medium for unmanned automatic car washing equipment. Background Art

[0002] Unmanned automatic car wash is a system that uses advanced technology to achieve automated cleaning. It mainly controls the car washing process through computer programs, reduces labor costs, and improves car washing efficiency. Unmanned automatic car wash includes multiple links such as vehicle positioning, pre-washing, main washing, rinsing and drying. Each link is interrelated. The completion of one link often affects the completion of the next link, so it is necessary to monitor the completion of each link.

[0003] However, since there is no staff to directly supervise the unmanned automatic car washing process, the staff can only analyze whether there are any abnormalities in each link through the transmitted data. This cannot avoid the occurrence of some occasional abnormalities, resulting in the need for staff to perform frequent maintenance, which seriously wastes staff energy and affects work efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide a remote fault monitoring and processing method and a storage medium for unmanned automatic car washing equipment to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a remote fault monitoring and processing method for unmanned automatic car washing equipment, the processing method comprising the following steps:

[0006] Step S100: Establish a car wash data management platform, transmit the data generated in each car wash process to the car wash data management platform and store it, and generate a number of car wash records; divide the data stored in any car wash record to obtain a number of links of the car wash record;

[0007] Step S200: setting corresponding evaluation rules for each link, randomly selecting a car wash record, evaluating each link of the car wash record, and obtaining the comprehensive completion degree of the car wash record;

[0008] Step S300: in the car wash record, after the vehicle is washed, the actual washing condition of the vehicle is detected to obtain the actual completion degree of the car wash record; by comparing the difference between the comprehensive completion degree and the actual completion degree of the car wash record, it is determined whether to perform the first feature mark on the car wash record;

[0009] Step S400: Summarize all car wash records without the first characteristic mark to generate a record set, perform difference analysis on the evaluation results of each link of each car wash record in the record set, and determine whether to perform the second characteristic mark on each car wash record in the record set;

[0010] Step S500: Acquire the car wash records without any characteristic mark, and analyze the correlation between any two adjacent links according to the data corresponding to each link; based on the correlation between each link, make an abnormal judgment on each link in the car wash records with the second characteristic mark, and obtain several risk links;

[0011] Step S600: Acquire all car wash records with the first characteristic mark and the second characteristic mark, and set the risk judgment conditions for each link based on the generation of each risk link;

[0012] Step S700: obtaining a latest real-time car wash record generated on the car wash data management platform, evaluating the cleaning status of the real-time car wash record, and determining whether to issue a risk warning for the real-time car wash record.

[0013] Furthermore, step S100 includes the following steps:

[0014] Step S101: randomly select a car wash record, obtain the data stored in the car wash record, and sort all the data according to the data storage time; obtain the data type of each data, and if there are two adjacent data with the same data type, set the two data as the same type of data;

[0015] Step S102: randomly select a data, obtain all similar data adjacent to and continuous with the data, and generate a link of the car wash record; divide the data stored in the car wash record into similar data, and obtain several links of the car wash record.

[0016] Further, step S200 includes the following steps:

[0017] Step S201: randomly obtain a car wash record, and obtain data of any link in the car wash record; and obtain the completion degree of each link according to the set evaluation rules;

[0018] Step S202: Set the completion degree of the i-th link in the car wash record to W i , according to the formula:

[0019]

[0020] Among them, W1 is the completion degree of the first link, W i+1is the completion degree of the i+1th link, a is the total number of links in the car wash record; the comprehensive completion degree C of the car wash record is calculated; there is a certain correlation between two adjacent links, so the completion degree of the previous link will affect the completion degree of the next link. In this way, a more accurate comprehensive completion degree can be obtained.

[0021] Further, step S300 includes the following steps:

[0022] Step S301: Obtain the actual completion degree and comprehensive completion degree of each car wash record, and calculate the average of the actual completion degree and comprehensive completion degree of each car wash record to obtain the average actual completion degree E eva and an average comprehensive completion rate of C eva , the error threshold is calculated to be θ=|E eva -C eva |;

[0023] Step S302: setting the actual completion degree of any selected car wash record to E and the comprehensive completion degree to C, obtaining the completion degree difference of the car wash record as ΔD=|EC|, and if ΔD≥θ, performing a first feature mark on the car wash record;

[0024] Step S303: If ΔD<θ, then obtain the minimum completion degree E allowed for any car wash record allow =E eva ×(1-θ), if E eva <C eva And E eva <E allow , then the car wash record is marked with a first feature;

[0025] The presence of the first characteristic mark indicates that there is an abnormality in the car wash record. When the difference between the comprehensive completion degree and the actual completion degree is large, it can directly reflect the abnormality; when the difference is not large, if the actual completion degree is very low, it can also indicate that an abnormal situation occurred during the car wash process, resulting in a low completion degree.

[0026] Furthermore, step S400 includes the following steps:

[0027] Step S401: Set the car wash record without the first feature mark as the target car wash record, select a target car wash record from the generated record set, and obtain the completion degree of the i-th link in the target car wash record as W i ;

[0028] Step S402: Calculate the average completion degree of the ith link in each target car wash record to obtain the average completion degree of the ith link in the record set (W i ) ave; Select the target car wash record with the highest completion degree of the i-th link, and set the maximum completion degree of the i-th link to (W i ) max , the minimum completion degree allowed for the i-th link is calculated as (W i ) min =(W i ) ave -[(W i ) max -(W i ) ave ]; if W i <(W i ) min , then a second feature mark is performed on the target car wash record;

[0029] The presence of the second characteristic mark indicates that the final completion of the car wash record is normal, but there are abnormalities in the intermediate links, which requires further analysis to help identify whether it is an occasional abnormality or a real abnormality in the link.

[0030] Further, step S500 includes the following steps:

[0031] Step S501: extracting all target car wash records without the second characteristic mark from the record set to obtain a normal car wash record set; arbitrarily selecting a normal car wash record from the normal car wash record set, and arbitrarily selecting two adjacent links from the normal car wash record;

[0032] Step S502: respectively obtain a number of data corresponding to the two links, and construct a correlation formula between the two links:

[0033] y=p×q z +r×z+t;

[0034] Among them, y is the data corresponding to the latter of the two links, z is the data corresponding to the former of the two links, and p, q, r and t are all constant coefficients; the association formula is trained through a number of data from the two links in any other normal car wash records to determine the values ​​of the constant coefficients p, q, r and t;

[0035] There will be a relationship between the values ​​of two adjacent links. For example, the amount of detergent used in the previous link will affect the amount of water used in the next link, and the amount of water used in the previous link will affect the subsequent drying time, etc. The established correlation formula includes exponential functions and linear functions, which can basically meet the correlation between each link, and can also provide reference data for the degree of correlation between subsequent links.

[0036] Step S503: arbitrarily select two normal car wash records, extract the data corresponding to the i-1th link in the two normal car wash records respectively and substitute them into the association formula, obtain the data of the i-th link as yi and yi' respectively, and obtain the data difference of the i-th link as Δyi=|yi-yi'|; respectively obtain the completion degree of the i-th link in the two normal car wash records as W i and W i ';According to the formula:

[0037]

[0038] It is calculated that in the two normal car wash records, the correlation degree between the i-1th link and the ith link is H i-1,i ; Calculate the average value of the correlation between the i-1th link and the i-th link in any two normal car wash records, and get the correlation between the i-1th link and the i-th link G i-1,i The comparison between the data difference and the degree of completion is the difference between the two links. By subtracting the difference from 1, the correlation between the two links can be obtained.

[0039] Step S504: randomly select a target car wash record with the second feature marker from the record set, and obtain the completion degree of the i-th link as W i , set the minimum completion degree allowed for the i-th link to be (W i ) min , if W i <(W i ) min , then obtain the completion degree W of the i-1th link i-1 , set the minimum completion degree allowed for the i-1th link to be (W i-1 ) min , if W i-1 ≥(W i-1 ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link. If W i-1 <(W i-1 ) min , then the adjusted completion degree of the i-th link is W i ’ =W i ×(1+G i-1,i ), if W i ’ <(W i ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link;

[0040] To determine whether a link with a low degree of completion is a risky link, in addition to its own degree of completion, it is also necessary to consider the completion of the previous link; if the previous link also has a low degree of completion, the impact of the previous link must be considered, and the current link must be adjusted before making a judgment, in order to effectively identify the risky link.

[0041] Further, step S600 includes the following steps:

[0042] Step S601: sorting the car wash records in the car wash data management platform from back to front according to the record generation time to obtain a car wash record queue, taking the car wash record with the first characteristic mark as a reference record, and dividing the car wash record queue into a plurality of sub-queues;

[0043] Step S602: arbitrarily select a subqueue, obtain the reference record before the subqueue, extract the risk link in the reference record, set the i-th link in the reference record as the risk link; count the number of records in which the i-th link in the subqueue is the risk link, and obtain the occurrence frequency of the i-th link as the risk link as f i ;

[0044] Step S603: extract the risk link in the first car wash record in the subqueue. If the i-th link is a risk link in the first car wash record, the number of consecutive times the i-th link is a risk link starting from the first car wash record is n. i ; Get the maximum number of consecutive risk links in which the i-th link in the subqueue is continuous, which is n max , if n i =n max , then the number of consecutive times n i As the condition for the i-th link to cause the reference record to be marked with the first feature, if n i <n max , then the frequency f will occur i As the condition that causes the reference record to be marked with the first feature in the i-th link; the abnormality judgment condition includes the occurrence frequency and the number of consecutive occurrences, both of which can most directly and effectively reflect the abnormality of the car wash record;

[0045] Step S604: Obtain the occurrence frequency and consecutive times of the i-th link in each sub-queue being a risk environment, and select the occurrence frequency with the smallest value (f i ) min and the number of consecutive times (n i ) min As the judgment condition for whether there is an abnormality in the i-th link in each car wash record.

[0046] Furthermore, step S700 includes the following steps:

[0047] Step S701: Obtain a real-time car wash record with the shortest time interval from the current moment, and obtain the actual completion degree E of the real-time car wash record now and overall completion degree C now , set the error threshold to θ, if |EC|≥θ, then issue a risk warning for the real-time car wash record;

[0048] Step S702: If |EC|<θ, the completion degree of each link of the real-time car wash record is obtained, and the risk of each link is identified; it is assumed that the i-th link in the real-time car wash record is a risk link, and a number of car wash records adjacent to and continuous to the real-time car wash record are obtained, and the frequency of the i-th link being a risk link in the several car wash records is obtained as (f i ) now And the number of consecutive times is (n i ) now , if (f i ) now >(f i ) min or (n i ) now >(n i ) min , a risk warning is issued for the real-time car wash record.

[0049] A storage medium stores computer instructions, which, when executed by a processor, can implement a remote fault monitoring and processing method for unmanned automatic car washing equipment.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. The present invention can help the staff ignore the abnormal situations not caused by equipment problems by effectively analyzing the occasional abnormalities in each link of the car washing process, thus avoiding frequent maintenance by the staff and improving the work efficiency of the staff;

[0052] 2. The present invention reasonably divides all historical car wash records by comparing the differences between the completion degree and comprehensive completion degree of each link in the historical car wash records, helps analyze the presentation of occasional abnormal data, and is conducive to accurately judging the abnormal situation of the car wash records in the future, thereby improving the efficiency of the staff;

[0053] 3. The present invention sets different abnormal judgment conditions for each link and combines the correlation between adjacent links to improve the relatively accurate abnormal judgment standard, which can accurately help staff identify abnormal conditions of car washing equipment and help staff accurately and quickly identify abnormal conditions and solve them. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of the steps of a remote fault monitoring and processing method for unmanned automatic car washing equipment. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example: Figure 1 As shown, the present invention provides a remote fault monitoring and processing method for unmanned automatic car washing equipment, and the processing method comprises the following steps:

[0057] Step S100: Establish a car wash data management platform, transmit the data generated in each car wash process to the car wash data management platform and store it, and generate a number of car wash records; divide the data stored in any car wash record to obtain a number of links of the car wash record;

[0058] Wherein, step S100 includes the following steps:

[0059] Step S101: randomly select a car wash record, obtain the data stored in the car wash record, and sort all the data according to the data storage time; obtain the data type of each data, and if there are two adjacent data with the same data type, set the two data as the same type of data;

[0060] Step S102: randomly selecting a data, obtaining all similar data adjacent to and continuous with the data, and generating a link of the car wash record; dividing the data stored in the car wash record into similar data, and obtaining several links of the car wash record;

[0061] Embodiment 1: It is assumed that different data types are obtained, such as water consumption, detergent consumption, drying time, etc., and the car wash record can be divided into three stages: rinsing, detergent washing, and drying.

[0062] Step S200: setting corresponding evaluation rules for each link, randomly selecting a car wash record, evaluating each link of the car wash record, and obtaining the comprehensive completion degree of the car wash record;

[0063] Wherein, step S200 includes the following steps:

[0064] Step S201: randomly obtain a car wash record, and obtain data of any link in the car wash record; and obtain the completion degree of each link according to the set evaluation rules;

[0065] Step S202: Set the completion degree of the i-th link in the car wash record to W i , according to the formula:

[0066]

[0067] Among them, W1 is the completion degree of the first link, W i+1 is the completion degree of the i+1th link, a is the total number of links in the car wash record; the comprehensive completion degree C of the car wash record is calculated;

[0068] Example 2: Assume that a car wash record has 4 links, and the completion degree of each link is 95%, 90%, 98% and 95% respectively. The comprehensive completion degree C is calculated to be C=(0.95+0.95×0.9+0.9×0.98+0.98×0.95) / 4=(0.95+0.855+0.882+0.931) / 4=90.45%;

[0069] Step S300: in the car wash record, after the vehicle is washed, the actual washing condition of the vehicle is detected to obtain the actual completion degree of the car wash record; by comparing the difference between the comprehensive completion degree and the actual completion degree of the car wash record, it is determined whether to perform the first feature mark on the car wash record;

[0070] Wherein, step S300 includes the following steps:

[0071] Step S301: Obtain the actual completion degree and comprehensive completion degree of each car wash record, and calculate the average of the actual completion degree and comprehensive completion degree of each car wash record to obtain the average actual completion degree E eva and an average comprehensive completion rate of C eva , the error threshold is calculated to be θ=|E eva -C eva |;

[0072] Step S302: setting the actual completion degree of any selected car wash record to E and the comprehensive completion degree to C, obtaining the completion degree difference of the car wash record as ΔD=|EC|, and if ΔD≥θ, performing a first feature mark on the car wash record;

[0073] Step S303: If ΔD<θ, then obtain the minimum completion degree E allowed for any car wash record allow =E eva ×(1-θ), if E eva <C eva And Eeva <E allow , then perform a first feature mark on the car wash record.

[0074] Step S400: Summarize all car wash records without the first characteristic mark to generate a record set, perform difference analysis on the evaluation results of each link of each car wash record in the record set, and determine whether to perform the second characteristic mark on each car wash record in the record set;

[0075] Wherein, step S400 includes the following steps:

[0076] Step S401: Set the car wash record without the first feature mark as the target car wash record, select a target car wash record from the generated record set, and obtain the completion degree of the i-th link in the target car wash record as W i ;

[0077] Step S402: Calculate the average completion degree of the ith link in each target car wash record to obtain the average completion degree of the ith link in the record set (W i ) ave ; Select the target car wash record with the highest completion degree of the i-th link, and set the maximum completion degree of the i-th link to (W i ) max , the minimum completion degree allowed for the i-th link is calculated as (W i ) min =(W i ) ave -[(W i ) max -(W i ) ave ]; if W i <(W i ) min , then a second feature mark is performed on the target car wash record;

[0078] Example 3: The completion degree of a link is set to 60%, the average completion degree of the link is set to 85%, and the maximum completion degree is set to 95%, so the minimum allowable completion degree is 75%. Because 60% < 75%, the corresponding target car wash record is marked as abnormal.

[0079] Step S500: Acquire the car wash records without any characteristic mark, and analyze the correlation between any two adjacent links according to the data corresponding to each link; based on the correlation between each link, make an abnormal judgment on each link in the car wash records with the second characteristic mark, and obtain several risk links;

[0080] Wherein, step S500 includes the following steps:

[0081] Step S501: extracting all target car wash records without the second characteristic mark from the record set to obtain a normal car wash record set; arbitrarily selecting a normal car wash record from the normal car wash record set, and arbitrarily selecting two adjacent links from the normal car wash record;

[0082] Step S502: respectively obtain a number of data corresponding to the two links, and construct a correlation formula between the two links:

[0083] y=p×q z +r×z+t;

[0084] Among them, y is the data corresponding to the latter of the two links, z is the data corresponding to the former of the two links, and p, q, r and t are all constant coefficients; the association formula is trained through a number of data from the two links in any other normal car wash records to determine the values ​​of the constant coefficients p, q, r and t;

[0085] Step S503: arbitrarily select two normal car wash records, extract the data corresponding to the i-1th link in the two normal car wash records respectively and substitute them into the association formula, and obtain the data of the i-th link as y i and i ’ , the data difference of the i-th link is Δy i =|y i -y i ’ |; respectively obtain the completion degree of the i-th link in the two normal car wash records as W i and W i ’ ; According to the formula:

[0086]

[0087] It is calculated that in the two normal car wash records, the correlation degree between the i-1th link and the ith link is H i-1,i ; Calculate the average value of the correlation between the i-1th link and the i-th link in any two normal car wash records, and get the correlation between the i-1th link and the i-th link G i-1,i ;

[0088] Step S504: randomly select a target car wash record with the second feature marker from the record set, and obtain the completion degree of the i-th link as W i , set the minimum completion degree allowed for the i-th link to be (W i ) min , if W i <(W i) min , then obtain the completion degree W of the i-1th link i-1 , set the minimum completion degree allowed for the i-1th link to be (W i-1 ) min , if W i-1 ≥(W i-1 ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link. If W i-1 <(W i-1 ) min , then the adjusted completion degree of the i-th link is W i ’ =W i ×(1+G i-1,i ), if W i ’ <(W i ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link.

[0089] Step S600: Acquire all car wash records with the first characteristic mark and the second characteristic mark, and set the risk judgment conditions for each link based on the generation of each risk link;

[0090] Wherein, step S600 includes the following steps:

[0091] Step S601: sorting the car wash records in the car wash data management platform from back to front according to the record generation time to obtain a car wash record queue, taking the car wash record with the first characteristic mark as a reference record, and dividing the car wash record queue into a plurality of sub-queues;

[0092] Step S602: arbitrarily select a subqueue, obtain the reference record before the subqueue, extract the risk link in the reference record, set the i-th link in the reference record as the risk link; count the number of records in which the i-th link in the subqueue is the risk link, and obtain the occurrence frequency of the i-th link as the risk link as f i ;

[0093] Step S603: extract the risk link in the first car wash record in the subqueue. If the i-th link is a risk link in the first car wash record, the number of consecutive times the i-th link is a risk link starting from the first car wash record is n. i ; Get the maximum number of consecutive risk links in which the i-th link in the subqueue is continuous, which is n max , if n i =n max , then the number of consecutive times n iAs the condition for the i-th link to cause the reference record to be marked with the first feature, if n i <n max , then the frequency f will occur i The condition that causes the reference record to be marked with the first feature as the i-th link;

[0094] Step S604: Obtain the occurrence frequency and consecutive times of the i-th link in each sub-queue being a risk environment, and select the occurrence frequency with the smallest value (f i ) min and the number of consecutive times (n i ) min As the judgment condition for whether there is an abnormality in the i-th link in each car wash record.

[0095] Step S700: obtaining a latest real-time car wash record generated on the car wash data management platform, evaluating the cleaning status of the real-time car wash record, and determining whether to issue a risk warning for the real-time car wash record;

[0096] Wherein, step S700 includes the following steps:

[0097] Step S701: Obtain a real-time car wash record with the shortest time interval from the current moment, and obtain the actual completion degree E of the real-time car wash record now and overall completion degree C now , set the error threshold to θ, if |EC|≥θ, then issue a risk warning for the real-time car wash record;

[0098] Step S702: If |EC|<θ, the completion degree of each link of the real-time car wash record is obtained, and the risk of each link is identified; it is assumed that the i-th link in the real-time car wash record is a risk link, and a number of car wash records adjacent to and continuous to the real-time car wash record are obtained, and the frequency of the i-th link being a risk link in the several car wash records is obtained as (f i ) now And the number of consecutive times is (n i ) now , if (f i ) now >(f i ) min or (n i ) now >(n i ) min , a risk warning is issued for the real-time car wash record.

[0099] A storage medium stores computer instructions, which, when executed by a processor, can implement a remote fault monitoring and processing method for unmanned automatic car washing equipment.

[0100] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A remote fault monitoring and processing method for unmanned automatic car washing equipment, characterized in that: The processing method comprises the following steps: Step S100: Establish a car wash data management platform, transmit the data generated in each car wash process to the car wash data management platform and store it, and generate a number of car wash records; divide the data stored in any car wash record to obtain a number of links of the car wash record; Step S200: setting corresponding evaluation rules for each link, randomly selecting a car wash record, evaluating each link of the car wash record, and obtaining the comprehensive completion degree of the car wash record; Step S300: in the car wash record, after the vehicle is washed, the actual washing condition of the vehicle is detected to obtain the actual completion degree of the car wash record; by comparing the difference between the comprehensive completion degree and the actual completion degree of the car wash record, it is determined whether to perform the first feature mark on the car wash record; Step S400: Summarize all car wash records without the first characteristic mark to generate a record set, perform difference analysis on the evaluation results of each link of each car wash record in the record set, and determine whether to perform the second characteristic mark on each car wash record in the record set; Step S500: Acquire the car wash records without any characteristic mark, and analyze the correlation between any two adjacent links according to the data corresponding to each link; based on the correlation between each link, make an abnormal judgment on each link in the car wash records with the second characteristic mark, and obtain several risk links; Step S600: Acquire all car wash records with the first characteristic mark and the second characteristic mark, and set the risk judgment conditions for each link based on the generation of each risk link; Step S700: obtaining a latest real-time car wash record generated on the car wash data management platform, evaluating the cleaning status of the real-time car wash record, and determining whether to issue a risk warning for the real-time car wash record.

2. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 1 is characterized in that: The step S100 includes the following steps: Step S101: randomly select a car wash record, obtain the data stored in the car wash record, and sort all the data according to the data storage time; obtain the data type of each data, and if there are two adjacent data with the same data type, set the two data as the same type of data; Step S102: randomly select a data, obtain all similar data adjacent to and continuous with the data, and generate a link of the car wash record; divide the data stored in the car wash record into similar data, and obtain several links of the car wash record.

3. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 2 is characterized in that: The step S200 includes the following steps: Step S201: randomly obtain a car wash record, and obtain data of any link in the car wash record; and obtain the completion degree of each link according to the set evaluation rules; Step S202: Set the completion degree of the i-th link in the car wash record to W i , according to the formula: Among them, W1 is the completion degree of the first link, W i+1 is the completion degree of the i+1th link, a is the total number of links in the car washing record; the comprehensive completion degree C of the car washing record is calculated.

4. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 3 is characterized in that: The step S300 includes the following steps: Step S301: Obtain the actual completion degree and comprehensive completion degree of each car wash record, and calculate the average of the actual completion degree and comprehensive completion degree of each car wash record to obtain the average actual completion degree E eva and an average comprehensive completion rate of C eva , the error threshold is calculated to be θ=|E eva -C eva |; Step S302: setting the actual completion degree of any selected car wash record to E and the comprehensive completion degree to C, obtaining the completion degree difference of the car wash record as ΔD=|EC|, and if ΔD≥θ, performing a first feature mark on the car wash record; Step S303: If ΔD<θ, then obtain the minimum completion degree E allowed for any car wash record allow =E eva ×(1-θ), if E eva <C eva And E eva <E allow , then the car wash record is marked with a first feature.

5. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: Set the car wash record without the first feature mark as the target car wash record, select a target car wash record from the generated record set, and obtain the completion degree of the i-th link in the target car wash record as W i ; Step S402: Calculate the average completion degree of the ith link in each target car wash record to obtain the average completion degree of the ith link in the record set (W i ) ave ; Select the target car wash record with the highest completion degree of the i-th link, and set the maximum completion degree of the i-th link to (W i ) max , the minimum completion degree allowed for the i-th link is calculated as (W i ) min =(W i ) ave -[(W i ) max -(W i ) ave ]; if W i <(W i ) min , then the target car wash record is marked with a second feature.

6. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 5 is characterized in that: The step S500 includes the following steps: Step S501: extracting all target car wash records without the second characteristic mark from the record set to obtain a normal car wash record set; arbitrarily selecting a normal car wash record from the normal car wash record set, and arbitrarily selecting two adjacent links from the normal car wash record; Step S502: respectively obtain a number of data corresponding to the two links, and construct a correlation formula between the two links: y=p×q z +r×z+t; Among them, y is the data corresponding to the latter of the two links, z is the data corresponding to the former of the two links, and p, q, r and t are all constant coefficients; the association formula is trained through a number of data from the two links in any other normal car wash records to determine the values ​​of the constant coefficients p, q, r and t; Step S503: arbitrarily select two normal car wash records, extract the data corresponding to the i-1th link in the two normal car wash records respectively and substitute them into the association formula, and obtain the data of the i-th link as y i and i ', the data difference of the i-th link is Δy i =|y i -y i '|; respectively obtain the completion degree of the i-th link in the two normal car wash records as W i and W i ';According to the formula: It is calculated that in the two normal car wash records, the correlation degree between the i-1th link and the ith link is H i-1,i ; Calculate the average value of the correlation between the i-1th link and the i-th link in any two normal car wash records, and get the correlation between the i-1th link and the i-th link G i-1,i ; Step S504: randomly select a target car wash record with the second feature marker from the record set, and obtain the completion degree of the i-th link as W i , set the minimum completion degree allowed for the i-th link to be (W i ) min , if W i <(W i ) min , then obtain the completion degree W of the i-1th link i-1 , set the minimum completion degree allowed for the i-1th link to be (W i-1 ) min , if W i-1 ≥(W i-1 ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link. If W i-1 <(W i-1 ) min , then the adjusted completion degree of the i-th link is W i '=W i ×(1+G i-1,i ), if W i '<(W i ) min , then the i-th link of the target car wash record with the second feature mark is set as a risk link.

7. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 6 is characterized in that: The step S600 includes the following steps: Step S601: sorting the car wash records in the car wash data management platform from back to front according to the record generation time to obtain a car wash record queue, taking the car wash record with the first characteristic mark as a reference record, and dividing the car wash record queue into a plurality of sub-queues; Step S602: arbitrarily select a subqueue, obtain the reference record before the subqueue, extract the risk link in the reference record, set the i-th link in the reference record as the risk link; count the number of records in which the i-th link in the subqueue is the risk link, and obtain the occurrence frequency of the i-th link as the risk link as f i ; Step S603: extract the risk link in the first car wash record in the subqueue. If the i-th link is a risk link in the first car wash record, the number of consecutive times the i-th link is a risk link starting from the first car wash record is n. i ; Get the maximum number of consecutive risk links in which the i-th link in the subqueue is continuous, which is n max , if n i =n max , then the number of consecutive times n i As the condition for the i-th link to cause the reference record to be marked with the first feature, if n i <n max , then the frequency f will occur i The condition that causes the reference record to be marked with the first feature as the i-th link; Step S604: Obtain the occurrence frequency and consecutive times of the i-th link in each sub-queue being a risk environment, and select the occurrence frequency with the smallest value (f i ) min and the number of consecutive times (n i ) min As the judgment condition for whether there is an abnormality in the i-th link in each car wash record.

8. The remote fault monitoring and processing method for unmanned automatic car washing equipment according to claim 7 is characterized in that: The step S700 includes the following steps: Step S701: Obtain a real-time car wash record with the shortest time interval from the current moment, and obtain the actual completion degree E of the real-time car wash record now and overall completion degree C now , set the error threshold to θ, if |EC|≥θ, then issue a risk warning for the real-time car wash record; Step S702: If |EC|<θ, the completion degree of each link of the real-time car wash record is obtained, and the risk of each link is identified; it is assumed that the i-th link in the real-time car wash record is a risk link, and a number of car wash records adjacent to and continuous to the real-time car wash record are obtained, and the frequency of the i-th link being a risk link in the several car wash records is obtained as (f i ) now And the number of consecutive times is (n i ) now , if (f i ) now >(f i ) min or (n i ) now >(n i ) min , a risk warning is issued for the real-time car wash record.

9. A storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed by the processor, the remote fault monitoring and processing method for the unmanned automatic car washing equipment according to any one of claims 1 to 8 can be implemented.

Images