Equipment quality information analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses an equipment quality information analysis method and device, electronic equipment and a storage medium. The method comprises the following steps: S1, acquiring historical equipment quality information; s2, constructing an equipment quality information analysis model based on deep learning according to historical equipment quality information; and S3, inputting to-be-processed equipment quality information into the equipment quality information analysis model for equipment quality management. By adopting the technical scheme of the invention, a technical solution is provided for troop equipment quality information management work.

Description

Technical Field

[0001] The present invention belongs to the field of information processing technology, and in particular relates to an equipment quality information analysis method and device, an electronic device, and a storage medium. Background Art

[0002] The collection and application of equipment quality information involves the entire process of equipment mobilization, maintenance, and resource consumption. It has the characteristics of multiple information types, large data volume, and great difficulty in collection. Under the traditional management model with manual registration and statistics as the core, the collection of equipment quality information has brought a heavy burden to the daily management of the grassroots units of the troops. At the same time, it is difficult to ensure the timeliness and accuracy of the information, which hinders the normal development of equipment quality management-related business work and cannot give full play to the decision-making support role of equipment quality information in the equipment management of the troops. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an equipment quality information analysis method and device, electronic equipment, and storage medium to provide a technical solution for the equipment quality information management work of the troops.

[0004] To achieve the above object, the present invention adopts the following technical solution:

[0005] A method for analyzing equipment quality information comprises the following steps:

[0006] Step S1, obtaining historical equipment quality information;

[0007] Step S2: construct an equipment quality information analysis model based on deep learning according to historical equipment quality information;

[0008] Step S3: input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

[0009] Preferably, the historical equipment quality information includes: basic equipment information, quality information generated during equipment use, quality information generated during equipment maintenance, and equipment warehouse information.

[0010] Preferably, in step S2, the equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity and quality statistical analysis component, and equipment quality improvement component.

[0011] The present invention also provides an equipment quality information analysis device, comprising:

[0012] Acquisition module, used to obtain historical equipment quality information;

[0013] A construction module is used to build an equipment quality information analysis model based on deep learning according to historical equipment quality information;

[0014] The analysis module is used to input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

[0015] Preferably, the historical equipment quality information includes: basic equipment information, quality information generated during equipment use, quality information generated during equipment maintenance, and equipment warehouse information.

[0016] Preferably, the equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity and quality statistical analysis component, and equipment quality improvement component.

[0017] The present invention also provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to implement the equipment quality information analysis method when executing the program stored in the memory.

[0018] The present invention also provides a storage medium, wherein the storage medium stores machine executable instructions, and when the machine executable instructions are called and executed by a processor, the machine executable instructions can prompt the processor to implement the equipment quality information analysis method.

[0019] The advantages and beneficial effects of the present invention are as follows:

[0020] The present invention applies the deep learning neural network model to the equipment quality information collection in the process of equipment use and support, and constructs an equipment quality information analysis model based on deep learning to provide a technical solution for the equipment quality information management of the troops. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 A flowchart of a method for analyzing equipment quality information according to an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of the structure of an equipment quality information analysis device according to an embodiment of the present invention; DETAILED DESCRIPTION

[0024] 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.

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Embodiment 1:

[0027] The embodiment of the present invention provides an equipment quality information analysis method, which is used to collect signals and data generated by information collection objects such as equipment, personnel, materials, and equipment involved in the equipment mobilization process during the equipment use and support process in digital, image, audio and video, radio frequency identification, etc., and extract information from the collected data using a neural network model, and associate, fuse, and store the data with basic data of troop equipment and support systems to form an equipment quality information database for analysis and applications such as equipment reliability, maintainability, supportability, support resource inventory and consumption, and equipment quantity and quality statistics, thereby providing reliable data support for equipment quality management and even troop training and combat decision-making.

[0028] like Figure 1 As shown, an embodiment of the present invention provides an equipment quality information analysis method, comprising the following steps:

[0029] Step S1, obtaining historical equipment quality information;

[0030] Step S2: construct an equipment quality information analysis model based on deep learning according to historical equipment quality information;

[0031] Step S3: input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

[0032] As an implementation of an embodiment of the present invention, the historical equipment quality information includes: basic equipment information, quality information generated during the equipment use process, quality information generated during the equipment maintenance process, and equipment material warehouse information.

[0033] Furthermore, basic equipment information, such as the equipment’s license plate number, motorcycle hours, and mileage, can be captured through handheld PDAs or smart cameras deployed at the entrance and exit of the parking lot, barcode (QR code) scanning, RFID recognition, and other devices;

[0034] The quality information generated during equipment maintenance includes: equipment number, equipment maintenance start and end time, maintenance personnel information, maintenance parts information and abnormal sounds, which can usually be obtained using cameras deployed in maintenance workshops that integrate intelligent recognition algorithms. Sound information can be collected through microphones, and liquid temperature can be obtained through temperature measuring instruments.

[0035] The quality information generated during the use of equipment includes: equipment number, equipment entry and exit time, and equipment quantity, which are also obtained by using smart cameras and other equipment deployed in the parking lot;

[0036] Equipment warehouse information includes the name, quantity and time of equipment entering and leaving the warehouse, which is usually obtained by smart cameras, barcode (QR code) scanning, RFID recognition and other devices deployed at the entrance of the equipment warehouse.

[0037] As an implementation method of the present invention, in step S2, YOLOv5 deep learning is adopted, and its network structure is mainly composed of four parts: Input, Backbone, Neck, and Prediction. Among them, Input adopts Mosaic data enhancement, adaptive anchor box calculation, adaptive image scaling and other technologies, Backbone adopts Focus and CSP structure, Neck part adopts FPN+PAN structure, and Prediction part adopts GIOU_Loss loss function. According to the difference of the two parameters of depth_multiple and width_multiple, the model scale can be divided into four models: YOLOv5x, YOLOv5l, YOLOv5m, and YOLOv5s.

[0038] As an implementation method of an embodiment of the present invention, in step S2, the equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity quality statistical analysis component, and equipment quality improvement component.

[0039] Furthermore, the equipment quality information analysis model analyzes historical equipment quality information, and can calculate equipment quality assessment parameters such as failure rate, availability, reliability, maintainability, and supportability of various types of equipment, evaluate the overall quality level of military equipment, and find out the weak links in equipment quality, so as to provide information support for equipment quality improvement and quality management. The specific analysis method is as follows. For ease of expression, a general operator function COUNT is defined here. i (x ij ), which represents the function of the two-dimensional parameter x ijThe specific data object sequence expressed is counted in the i dimension, regardless of its value; when the parameter has only one dimension, the function can be simplified to COUNT(x i ); when the parameter expression is a logical expression or a conditional expression, such as x ij >0, etc., then the function indicates that the object it counts is a data element that conforms to the logical or conditional expression, such as COUNT i (x ij >0) indicates counting the two-dimensional data object sequence whose value is greater than 0 in the i dimension.

[0040] Equipment reliability analysis component: Equipment reliability refers to the ability and reliability of equipment to perform specific functions under specified conditions. The equipment integrity can be obtained by calculating the mean time between failures, the mean time between equipment repairs, and the mean time between maintenance, thereby evaluating the equipment's ability to start performing tasks at any time. Equipment reliability analysis mainly records the equipment's combat and technical status through information collection equipment deployed in maintenance workshops and on-board information collection terminals, which include the equipment's mean time between failures, mean time between maintenance, etc. The above information can be used to calculate reliability parameters such as equipment availability and equipment integrity.

[0041] Mean time between failures (MTBF): A basic reliability parameter that reflects repairable products. According to GJB451A-2005 "Reliability, Maintainability and Support Terms", the mean time between failures is shown in Formula 1, which refers to the ratio of the total number of product life units to the total number of failures under specified conditions and time.

[0042]

[0043] The MTBF of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0044] The metadata involved include:

[0045] 1. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0046] 2. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0047] 3. Equipment establishment number: ENS;

[0048] 4. The time each piece of equipment enters the repair shop: E_CJ_INT ij , i = the time when the j-th equipment enters the workshop for the i-th time;

[0049] 5. The type of each equipment repair: E_WX_TYPE ij >0, the jth piece of equipment enters the workshop for the i-th time to perform preventive maintenance.

[0050] The mining calculation process is as follows:

[0051] 1. Calculate the usage time of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , EUT ij is the time when the jth piece of equipment is used for the i-th time;

[0052] 2. Calculate the total equipment usage time: TUT is the total usage time of all equipment;

[0053] 3. Calculate the number of times each piece of equipment enters the repair shop: WX j =COUNT i (E_CJ_INT ij ), WX j is the total number of times the jth piece of equipment enters the workshop;

[0054] 4. Calculate the number of preventive maintenance for each piece of equipment: WXP j =COUNT i (E_WX_TYPE ij >0), WXP j is the total number of times the jth piece of equipment enters the workshop for preventive maintenance;

[0055] 5. Calculate the total number of failures for each device: WXC j =WX j -WXP j , WXC j is the number of times the jth vehicle is repaired;

[0056] 6. Calculate the total number of equipment failures: WXC is the total number of equipment failures;

[0057] 7. Calculate the MTBF of the equipment: MTBF = TUT / WXC.

[0058] Mean time between maintenance (MTBM): As shown in Formula 2, it refers to the ratio of the total number of product life units to the total number of planned maintenance and unplanned maintenance events of the product under specified conditions and time.

[0059]

[0060] The MTBM of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0061] The metadata involved include:

[0062] 1. The time each equipment enters the maintenance workshop: E_CJ_INT ij , i = the time when the j-th equipment enters the workshop for the i-th time;

[0063] 2. The type of corrective repair for each piece of equipment: E_WX_TYPE ij =1, the jth piece of equipment enters the workshop for the ith time to perform corrective maintenance;

[0064] 3. The type of preventive maintenance for each piece of equipment: E_WX_TYPE ij > 0, the jth piece of equipment enters the workshop for the i-th time to perform preventive maintenance;

[0065] 4. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0066] 5. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0067] 6. Equipment establishment number: ENS.

[0068] The mining calculation process is as follows:

[0069] 1. Calculate the usage time of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment;

[0070] 2. Calculate the total equipment usage time: Total usage time of all equipment;

[0071] 3. Calculate the number of times each piece of equipment enters the repair shop: WX j =COUNT i (E_CJ_INT ij ), the total number of times the jth piece of equipment enters the workshop;

[0072] 4. Calculate the number of preventive maintenance for each piece of equipment: WXP j =COUNT i (E_WX_TYPE ij >0), the total number of times the jth equipment enters the workshop for preventive maintenance;

[0073] 5. Calculate the number of corrective repairs for each piece of equipment: WXC j =WX j -WXP j, the number of corrective maintenance of the jth vehicle;

[0074] 6. Calculate the total number of equipment maintenance times: Total number of equipment repairs;

[0075] 7. Calculate the mean time between maintenance: MTBM = TUT / WXN.

[0076] Mean time between failures (MTBF) of components j :Through statistical analysis of equipment use and maintenance information, the reliability level of equipment parts is statistically analyzed, such as the mean time between failures of parts, so as to evaluate the overall quality level of various equipment parts. The mean time between failures of equipment parts can be calculated using the following formula:

[0077]

[0078] Suppose the MTBF table of the jth component is MTBF j , calculate the MTBF of each component of the equipment by mining the collected metadata j , the specific mining calculation method is as follows:

[0079] The metadata involved include:

[0080] 1. Number of certain parts per piece of equipment: SNUM ij , the number of the j-th component in the i-th equipment;

[0081] 2. Equipment establishment number: ENS;

[0082] 3. Total number of equipment parts and components: PTN;

[0083] 4. Quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0084] 5. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0085] 6. Each instrumented motorcycle hours: UMH j , the current usage hours of the jth equipment;

[0086] 7. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0087] 8. Time each equipment is used each time: E_CC_OUT ij , the time when the j-th equipment appears for the i-th time.

[0088] The mining calculation process is as follows:

[0089] 1. Calculate the usage time of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment;

[0090] 2. Calculate the total equipment usage time: Total usage time of all equipment;

[0091] 3. Calculate the total consumption of each component: The total number of parts requested for the jth type; 4. Calculate the total number of each part in use: The total number of parts of the jth type in use;

[0092] 5. Calculate the MTBF of each component: MTBF j =(TUT×SNUM j ) / SCN j , the mean time between failures of the jth component.

[0093] Equipment maintainability analysis component: reflects the ability of equipment to recover functions. When repaired according to the prescribed methods and procedures, it is the ability of the equipment to maintain and recover to the prescribed state under the prescribed conditions and time. Equipment maintainability mainly uses acquisition equipment to collect images, videos, numbers, and text of the repair process, as well as equipment fluid temperature, sound, etc., and records vehicle number information, equipment motorcycle hours, repair personnel information, and repair man-hours to explore fault patterns, optimize repair processes, improve the efficiency of equipment repairs, and provide information support for equipment failure prevention. Equipment maintainability parameters mainly include average preventive maintenance time, average corrective maintenance time, and maintenance man-hour rate per unit motorcycle hour.

[0094] Mean preventive maintenance time MPMT: As shown in Formula 4, it refers to the ratio of the total preventive maintenance time of equipment to the total number of preventive maintenance under specified conditions. It does not include maintenance operations performed while the equipment is working, nor does it include supply and management delays.

[0095]

[0096] The MPMT of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0097] The metadata involved include:

[0098] 1. End time of each preventive maintenance for each equipment: E_CJ_OUT ij (E_WX_TYPE ij>0), the time when the jth equipment leaves the workshop for the i-th preventive maintenance;

[0099] 2. The start time of each preventive maintenance for each equipment: E_CJ_INT ij (E_WX_TYPE ij >0), the time when the jth equipment enters the workshop for the i-th preventive maintenance;

[0100] 3. The identifier of each preventive maintenance performed on each piece of equipment: E_WX_TYPE ij > 0, the jth piece of equipment enters the workshop for the i-th time to perform preventive maintenance;

[0101] 4. Equipment establishment number: ENS.

[0102] The mining calculation process is as follows:

[0103] 1. Calculate the number of preventive maintenance for each piece of equipment: WXP j =COUNT i (E_WX_TYPE ij >0), the total number of times the jth equipment enters the workshop for preventive maintenance;

[0104] 2. Calculate the total number of preventive maintenance: The total number of preventive maintenance performed on the equipment;

[0105] 3. Calculate the preventive maintenance time for each piece of equipment:

[0106] E_PWT ij =E_CJ_OUT ij (E_WX_TYPE ij >0)-E_CJ_INT ij (E_WX_TYPE ij >0), the time of the i-th preventive maintenance of the j-th equipment;

[0107] 4. Calculate the total preventive maintenance time: Total time for equipment preventive maintenance;

[0108] 5. Calculate the average preventive maintenance of equipment: MPMT = PWT / WPN, the average preventive maintenance time of equipment.

[0109] Mean corrective maintenance time MCMT: refers to the ratio of the total corrective maintenance time of equipment to the total number of corrective maintenance of the repaired equipment under specified conditions. The calculation formula is shown in Formula 5.

[0110]

[0111] The MCMT of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0112] The metadata involved include:

[0113] 1. The end time of each corrective maintenance of each equipment: E_CJ_OUT ij (E_WX_TYPE ij =0), the time when the j-th equipment leaves the workshop for the i-th corrective maintenance;

[0114] 2. The start time of each corrective repair of each equipment: E_CJ_INT ij (E_WX_TYPE ij =0), the time when the j-th equipment enters the workshop for the i-th corrective maintenance;

[0115] 3. The identifier of each corrective maintenance performed on each piece of equipment: E_WX_TYPE ij = 0, the jth piece of equipment enters the workshop for the i-th time to perform corrective maintenance;

[0116] 4. Equipment establishment number: ENS.

[0117] The mining calculation process is as follows:

[0118] 1. Calculate the time required for each corrective maintenance of each piece of equipment:

[0119] E_CWT ij =E_CJ_OUT ij (E_WX_TYPE ij =0)-E_CJ_INT ij (E_WX_TYPE ij =0), the time of the i-th corrective maintenance of the j-th equipment;

[0120] 2. Calculate the total time for corrective maintenance: The total time for corrective maintenance of equipment;

[0121] 3. Calculate the total number of corrective repairs for each piece of equipment: WXC j =COUNT i (E_WX_TYPE ij =0), the total number of times the jth equipment enters the workshop for corrective maintenance;

[0122] 4. Calculate the total number of corrective repairs for equipment: The total number of corrective repairs performed on the equipment;

[0123] 5. Calculate the average corrective maintenance time of equipment: MCMT = CWT / WCN, the average corrective maintenance time of equipment.

[0124] Maintenance man-hour rate per motor hour (MRH): refers to the total number of maintenance man-hours of the equipment divided by the total number of motor hours of the equipment. The unit is man-hour / motor hour. The calculation formula is shown in Formula 6.

[0125]

[0126] The MRH of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0127] The metadata involved include:

[0128] 1. The time each equipment leaves the workshop: E_CJ_OUT ij (F_WP_ID ij = k), the time when the jth equipment leaves the workshop for the i-th maintenance. The maintenance work is carried out at the k-th station.

[0129] 2. The time each piece of equipment enters the workshop: E_CJ_INT ij (F_WP_ID ij = k), the time when the jth equipment enters the workshop for maintenance for the ith time. The maintenance work is carried out at the kth station.

[0130] 3. Personnel participating in maintenance work: M_CS_INT ij (F_WP_ID ij =k), the jth maintenance personnel enters the kth workstation during the ith maintenance work.

[0131] 4. Initial motorcycle hours for each equipment: OMH j , the initial motorcycle hours of the jth equipment.

[0132] 5. Each instrumented motorcycle hours: UMH j , the existing motorcycle hours of the jth equipment.

[0133] 6. Equipment establishment number: ENS.

[0134] The mining calculation process is as follows:

[0135] 1. Calculate the total number of personnel for each maintenance task for each piece of equipment:

[0136] MMC ij =MCOUNT(M_CS_INT ij (F_WP_ID ij = k)), the total number of personnel participating in the maintenance task of the jth equipment in the i-th maintenance task. The MCOUNT function is a function for counting the number of personnel. This function means that the number of personnel participating in the maintenance is counted instead of the number of times, that is, no matter how many different personnel participate in a maintenance task, they are all counted as 1 person.

[0137] 2. Calculate the total maintenance hours for each piece of equipment:

[0138] MMH ij =MMC ij ×(E_CJ_OUT ij (F_WP_ID ij = k)-E_CJ_INT ij (F_WP_ID ij =k)), the total working hours for the i-th maintenance of the j-th equipment.

[0139] 3. Total equipment maintenance hours: Total maintenance hours for all equipment.

[0140] 4. Total motorcycle hours consumed by each equipment: MH j =UMH j -OMH j , motorcycle hours consumed by each equipment.

[0141] 5. Total motorcycles consumed by all equipment: Total motorcycle hours consumed by all equipment.

[0142] 6. Maintenance man-hour rate per motorcycle hour: MRH = MMH / TMH, maintenance man-hour per motorcycle hour.

[0143] Equipment supportability analysis component: refers to the ability of the equipment's design characteristics and planned support resources to meet the requirements of peacetime combat readiness and wartime use. Equipment supportability reflects the level of equipment's ease of support and acceptance of support, and is also an important basis for evaluating equipment design quality and use quality. Through the analysis and mining of equipment quality information, the main parameters of equipment supportability that can be obtained include equipment integrity rate, operational availability, average support delay time, support cost, etc.

[0144] Equipment readiness rate ER: As shown in Formula 7, it refers to the ratio of the number of equipment that can perform combat missions at any time to the actual number of equipment. It mainly reflects the combat readiness quality and combat readiness of the equipment. It is an important decision-making basis for troop combat and equipment use and maintenance.

[0145]

[0146] The ER of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0147] The metadata involved include:

[0148] 1. Equipment establishment number: ENS;

[0149] 2. Equipment maintenance status in the workshop: E_CJ_STAY j , a value of TRUE indicates that equipment j is under repair, and a value of FALSE indicates that equipment j is not under repair;

[0150] 3. Identification of the type of maintenance task performed by the equipment in the workshop: E_WX_TYPE j , the metadata values ​​include: 0-corrective repair, 1-minor repair, 2-medium repair, 3-major repair, 4-other repair.

[0151] The mining calculation process is as follows:

[0152] 1. Calculate the number of faulty equipment: ENF, the number of equipment that is in a state of failure (including those under repair),

[0153]

[0154] 2. Calculate the number of overhauled equipment: ENDM, the number of equipment under overhaul,

[0155]

[0156] 3. Calculate the number of equipment under repair: ENIM, the number of equipment under repair,

[0157]

[0158] 4. Calculate the number of equipment under minor repair: ENOM, the number of equipment under minor repair,

[0159]

[0160] 5. Calculate the number of other maintenance equipment: ENEM, the number of equipment in other maintenance,

[0161]

[0162] 6. Calculate equipment availability:

[0163] ER=(E_CJ_INT ij -ENF-ENDM-ENIM-ENOM-ENEM) / ENS.

[0164] Availability Ao is an important indicator that characterizes the integrity of equipment. It refers to the probability that the equipment is in an available state under the actual use environment. It is usually expressed by Formula 7, where the downtime includes the time used for preventive maintenance, the use guarantee time and the delay time.

[0165]

[0166] Calculate the equipment’s A by mining the collected metadata o, the specific mining calculation method is as follows:

[0167] The metadata involved include:

[0168] 1. The time each piece of equipment leaves the maintenance organization: E_JG_OUT ij , the time when the j-th equipment leaves the maintenance organization for the i-th maintenance;

[0169] 2. The time each piece of equipment enters the maintenance organization: E_JG_INT ij , the time when the j-th equipment enters the maintenance organization for the i-th maintenance;

[0170] 3. Starting time for each equipment statistics: STS j , the start time of the statistics of the jth equipment;

[0171] 4. The deadline for each equipment statistics: STE j , the deadline for statistics of the jth equipment;

[0172] 5. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0173] 6. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0174] 7. Initial motorcycle hours for each equipment: OMH ij , the initial motor hours of the jth equipment;

[0175] 8. Each instrument motorcycle hours: UMH ij , the number of motorcycle hours used by the current instrument of the jth equipment;

[0176] 9. Equipment establishment number: ENS.

[0177] The mining calculation process is as follows:

[0178] 1. Calculate the usage time of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment;

[0179] 2. Calculate the total working time of the equipment: Total operating time of the equipment;

[0180] 3. Calculate the downtime of each piece of equipment: EDT ij =E_JG_OUT ij -E_JG_INT ij, the total downtime of the j-th equipment entering the maintenance organization for the i-th time;

[0181] 4. Calculate the total equipment downtime: Total equipment downtime;

[0182] 5. Calculate the total equipment system time: The total time of each equipment;

[0183] 6. Calculate the availability of equipment: A o =(STT-EDT) / STT.

[0184] Mean support delay time (MSDT): refers to the average value of the delay time for equipment maintenance in order to obtain necessary maintenance resources such as maintenance personnel, spare parts, and test equipment. It is usually measured by the ratio of the total support delay time of the equipment to the total number of failures within a specified time. The mean support delay time is an important parameter for optimizing support resources. Its calculation formula is shown in Formula 9.

[0185]

[0186] In this system, the MSDT of the equipment is calculated by mining the collected metadata. The specific mining and calculation method is as follows: The metadata involved includes:

[0187] 1. The time each equipment enters the workshop: E_CJ_INT ij , the time when the j-th equipment enters the workshop for maintenance for the i-th time;

[0188] 2. The time each piece of equipment enters the repair facility: E_JG_INT ij , the time when the j-th equipment enters the maintenance organization for the i-th maintenance;

[0189] 3. Equipment establishment number: ENS;

[0190] 4. Equipment type identification for each repair task: E_WX_TYPE ij =1, the j-th equipment enters the workshop for the i-th time to perform preventive maintenance.

[0191] The mining calculation process is as follows:

[0192] 1. Calculate the number of times each piece of equipment enters the repair shop: WX j =COUNT i (E_CJ_INT ij ), the total number of times the jth piece of equipment enters the workshop;

[0193] 2. Calculate the number of preventive maintenance for each piece of equipment: WXP j =COUNT i(E_WX_TYPE ij =1), the total number of times the jth equipment enters the workshop for preventive maintenance;

[0194] 3. Calculate the number of failures of each device: WXC j =WX j -WXP j , the number of times the jth vehicle is repaired;

[0195] 4. Calculate the total number of equipment failures:

[0196] 5. Calculate the maintenance delay time of each equipment: MDT ij =E_CJ_INT ij -E_JG_INT ij ;

[0197] 6. Calculate the total equipment support delay time:

[0198] 7. Calculate the average equipment support delay time: MSDT = MDT / WXC.

[0199] Support cost: refers to the value of human resources, spare parts and other resources consumed during the use, repair, maintenance and scrapping of equipment. By calculating and analyzing the equipment support cost, the support process can be optimized, the military economic benefits can be maximized, and the cost-effectiveness of fund use can be improved. Equipment support costs are usually characterized by a variety of different types of parameters that reflect equipment support costs, mainly including utilization parameters of facilities, spare parts, personnel, equipment, etc. In this system, various support cost parameters of equipment are calculated by mining the collected metadata. The specific mining and calculation methods are as follows:

[0200] The metadata involved include:

[0201] 1. The quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0202] 2. Unit price of each spare part: SPV j ;

[0203] 3. Weight of each spare part: SPW j ;

[0204] 4. Spare parts number: SPN;

[0205] 5. Total number of maintenance personnel: MTN;

[0206] 6. Manpower unit hourly cost: MPH, manpower cost per hour (RMB);

[0207] 7. Time each maintenance personnel enters the maintenance workshop each time: M_CS_INT ij , the time when the jth maintenance personnel enters the maintenance workshop for the ith time;

[0208] 8. The time each maintenance personnel leaves the maintenance workshop: M_CS_OUT ij , the time when the jth maintenance personnel leaves the maintenance workshop for the ith time;

[0209] 9. Quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the j-th spare part requested for the i-th time.

[0210] The mining calculation process is as follows:

[0211] 1. Total spare parts consumption quantity: SPCTN

[0212] (1) Calculate the quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0213] (2) Calculate the total consumption of each component: The total number of requests for the jth type of parts;

[0214] (3) Calculate the total consumption of spare parts:

[0215] 2. Total weight of spare parts consumption: SPCTW

[0216] (1) Calculate the total consumption of each component: The total number of requests for the jth type of parts;

[0217] (2) Calculate the total weight of spare parts consumed:

[0218] Total manpower cost MPTC

[0219] (1) Calculate the total working time of each maintenance personnel: The total working time of the jth maintenance personnel;

[0220] (2) Calculate the total maintenance workload: The sum of the total working hours of all maintenance personnel, that is, the total working hours of all maintenance work;

[0221] (3) Calculate the total labor cost: MPTC = MPH × MWT.

[0222] Average maintenance workload MMPH

[0223] (1) Calculate the total working time of each maintenance personnel: The total working time of the jth maintenance personnel;

[0224] (2) Calculate the total maintenance workload: The sum of the total working hours of all maintenance personnel, that is, the total working hours of all maintenance work;

[0225] (3) Calculate the average maintenance workload: MMPH = MWT / MTN.

[0226] Spare parts protection total cost SPCTC

[0227] (1) Calculate the total consumption of each component: The total number of requests for the jth type of parts;

[0228] (2) Calculate the total cost of spare parts support:

[0229] Support resource usage and consumption analysis component: refers to the analysis of the accumulated data of equipment quality information collected over a certain period of time, which helps equipment management personnel to grasp the equipment support resource allocation level and usage and consumption. Based on this, it can realize the refined allocation, scheduling and optimization of spare parts, support equipment, manpower, support facilities and other resources required for equipment during use and maintenance, thereby improving the utilization rate of various support resources, optimizing the establishment or inventory quantity and type, saving equipment support and troop management costs, and improving the work efficiency of equipment support.

[0230] FUR: FUR is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0231] The metadata involved include:

[0232] 1. The statistical start time of each facility: FTS j , the start time of the jth facility statistics;

[0233] 2. Statistical cutoff time for each facility: FTE j , the deadline for statistics of the jth facility;

[0234] 3. Equipment ID: E_ID j , the ID of the jth equipment;

[0235] 4. ID of the object entering the facility: F_OBJ_IN_ID;

[0236] 5. The start time of each facility being occupied: F_OBJ_INT ij (F_OBJ_IN_ID∈E_ID), the time when the jth facility is occupied by the i-th equipment;

[0237] 6. End time of each facility being occupied: F_OBJ_OUT ij (F_OBJ_IN_ID∈E_ID), the time when the jth facility is occupied by the i-th equipment and then leaves;

[0238] 7.Total number of facilities: FTN.

[0239] The mining calculation process is as follows:

[0240] 1. Calculate the total working hours for each facility:

[0241] FWT j =∑(F_OBJ_OUT ij (F_OBJ_IN_ID∈E_ID)-F_OBJ_INT ij (F_OBJ_IN_ID∈E_ID)), the total time the jth facility is occupied;

[0242] 2. Calculate the total facility time:

[0243] 3. Calculate facility utilization: The ratio of the sum of the working hours of all facilities to the total working hours of all facilities.

[0244] Equipment utilization rate TUR: TUR is calculated by mining the collected metadata. The specific mining calculation method is as follows:

[0245] The metadata involved include:

[0246] 1. The start time of each device being occupied: T_BUSY_T ij , the start time of the ith occupation of the jth device;

[0247] 2. The end time of each device being occupied: T_RELEASE_T ij , the time when the jth device is released after the i-th occupation; 3. The statistical start time of each device: TTTS j , the start time of the jth device statistics (hours);

[0248] 4. Statistical cutoff time for each device: TTTE j , the deadline for statistics of the jth device (hours);

[0249] 5.Total number of devices: TTN.

[0250] The mining calculation process is as follows:

[0251] 1. Calculate the total working time of each device: The total occupied time of the jth device;

[0252] 2. Calculate the total device time: Calculated based on 8 hours of working time per day;

[0253] 3. Calculate equipment utilization: The ratio of the sum of the working time of all devices to the total working time of all devices.

[0254] Personnel utilization rate (MUR): MUR is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0255] The metadata involved include:

[0256] 1. The statistical start time of each maintenance personnel: MTS j , the start time (hours) of the jth maintenance personnel statistics;

[0257] 2. Statistical deadline for each maintenance personnel: MTE j , the deadline for statistics of the jth maintenance personnel (hours);

[0258] 3. Total number of maintenance personnel: MTN;

[0259] 4. The time each maintenance personnel enters the maintenance workshop each time: M_CS_INT ij , the time when the jth maintenance personnel enters the maintenance workshop for the ith time;

[0260] 5. The time each maintenance personnel leaves the maintenance workshop: M_CS_OUT ij , the time when the j-th maintenance personnel leaves the maintenance workshop for the i-th time.

[0261] The mining calculation process is as follows:

[0262] 1. Calculate the total working time of each maintenance personnel: The total working time of the jth maintenance personnel;

[0263] 2. Calculate the total time of personnel: Calculated based on 8 hours of working time per day;

[0264] 3. Calculate staff utilization:

[0265] Average spare parts support delay time MDTSS: MDTSS is calculated by mining the collected metadata. The specific mining calculation method is as follows:

[0266] The metadata involved include:

[0267] 1. The time for each spare part to be checked out of the warehouse: S_CHECKOUT_T ij, the delivery time of the i-th request for the j-th spare part;

[0268] 2. Time for each spare part to be claimed: S_RQ_T ij , the time of the i-th request for the j-th spare part;

[0269] 3. Spare parts number: SPN.

[0270] The mining calculation process is as follows:

[0271] 1. Calculate the total support delay time for each spare part: Total support delay time for the jth type of spare parts;

[0272] 2. Calculate the total number of requests for each spare part: SRT j =COUNT i (S_RQ_T ij ), the total number of requests for the jth type of spare parts;

[0273] 3. Calculate the average spare parts support delay time:

[0274] Total spare parts consumption quantity SPCTN: SPCTN is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0275] The metadata involved include:

[0276] 1. The quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0277] 2. Spare parts number: SPN.

[0278] The mining calculation process is as follows:

[0279] 1. Calculate the total consumption of each component: 1. Calculate the total number of spare parts consumed:

[0280] Total weight of spare parts consumed (SPCTW): SPCTW is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0281] The metadata involved include:

[0282] 1. The quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0283] 2. Weight of each spare part: SPW j ;

[0284] 3. Spare parts number: SPN.

[0285] The mining calculation process is as follows:

[0286] 1. Calculate the total consumption of each component: The total number of requests for the jth type of parts;

[0287] 2. Calculate the total weight of spare parts consumption:

[0288] Equipment quantity and quality statistics component: Equipment quantity and quality information includes the type, quantity, vehicle condition, vehicle mobilization status, etc. of the equipment. After the equipment quality information is collected, the quantity and quality information can be displayed in real time, statistically summarized, etc. Based on the statistical analysis of the quantity and quality of equipment and its support resources, it can assist in optimizing and adjusting the future equipment use and support work plan, optimize the specific arrangements of various tasks and the supply of resources, improve the overall efficiency of support work, and provide accurate and timely information support for the troops to carry out equipment support, daily equipment management, equipment census, support plan formulation and even combat command.

[0289] Good Equipment Quantity (ERN): ERN is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0290] The metadata involved include:

[0291] 1. Identification of the type of maintenance task performed by the equipment: E_WX_TYPE j ;

[0292] 2. Equipment stays in the workshop for maintenance: E_CJ_STAY j ;

[0293] 3. Equipment establishment number: ENS.

[0294] The mining calculation process is as follows:

[0295] 1. Calculate the number of faulty equipment:

[0296] 2. Calculate the number of overhauled equipment:

[0297] 3. Calculate the number of repair equipment:

[0298] 4. Calculate the number of minor repair equipment:

[0299] 5. Calculate the number of other maintenance equipment:

[0300]

[0301] 6. Calculate the number of intact equipment: ERN = ENS-ENF-ENDM-ENIM-ENOM-ENEM.

[0302] Equipment training workload EUT: EUT is calculated by mining the collected metadata. The specific mining calculation method is as follows:

[0303] The metadata involved include:

[0304] 1. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0305] 2. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0306] 3. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0307] 4. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0308] 5. Equipment establishment number: ENS.

[0309] The mining calculation process is as follows:

[0310] 1. Calculate the usage time of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment;

[0311] 2. Calculate the total training workload for each device: The total training workload of the jth equipment in the statistical period;

[0312] 3. Calculate the total training workload of all equipment: The total training workload of all equipment during the statistical period.

[0313] Equipment Average Training Effort MEUT: MEUT is calculated by mining the collected metadata. The specific mining calculation method is as follows:

[0314] The metadata involved include:

[0315] 1. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0316] 2. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0317] 3. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0318] 4. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0319] 5. Equipment establishment number: ENS.

[0320] The mining calculation process is as follows:

[0321] 1. Time of use of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment; 2. The total training workload of each equipment: The total training workload of the jth equipment in the statistical period; 3. Calculate the average training workload of the equipment: The total training workload of all equipment during the statistical period.

[0322] Equipment technical status distribution: Equipment technical status distribution is usually represented by a variety of parameters that reflect the overall status of equipment technology. In this system, the distribution parameters of various equipment technical statuses are statistically calculated by mining the collected metadata. The specific mining and calculation methods are as follows:

[0323] The metadata involved include:

[0324] 1. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0325] 2. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0326] 3. Class I equipment motorcycle hour standard: EFCS;

[0327] 4. Motorcycle hour standard for Category II equipment: ESCS;

[0328] 5. Motorcycle hour standards for three types of equipment: ETCS;

[0329] 6. Key equipment used motorcycle hour standard: EMUS;

[0330] 7. General use equipment motorcycle hour standard: EGUS;

[0331] 8. Limited use equipment motorcycle hour standards: ECUS;

[0332] 9. Identification of the type of maintenance task performed by the equipment: E_WX_TYPE j ;

[0333] 10. Equipment stays in the workshop for maintenance: E_CJ_STAY j ;

[0334] 11. Equipment establishment number: ENS.

[0335] The mining calculation process is as follows:

[0336] 1. Count the number of faulty equipment: ENF, the number of equipment under repair.

[0337]

[0338] 2. Statistics on the number of equipment under overhaul: ENDM, the number of equipment under overhaul.

[0339]

[0340] 3. Statistics on the number of equipment under repair: ENIM, the number of equipment under repair.

[0341]

[0342] 4. Statistics on the number of equipment in minor repair: ENOM, the number of equipment in minor repair.

[0343]

[0344] 5. Statistics on the number of other equipment under maintenance: ENEM, the number of equipment under other maintenance.

[0345]

[0346] 6. Count the number of equipment in one category:

[0347] 7. Count the number of Category II equipment:

[0348] 8. Count the number of three types of equipment:

[0349] 9. Statistical focus on the number of equipment used:

[0350] 10. Statistics of the number of equipment in general use:

[0351] 11. Statistical restrictions on the number of equipment used:

[0352] 12. Calculate the number of combat-ready equipment: ENIR = EFCN + ESCN + ETCN;

[0353] 13. Calculate the number of coach equipment: ENIT = EMUN + EGUN + ECUN;

[0354] 14. Calculate the combat-teaching ratio: ROWT = ENIR / ENIT;

[0355] 15. Calculate the availability rate:

[0356] ER=(E_CJ_INT ij -ENF-ENDM-ENIM-ENOM-ENEM) / ENS;

[0357] 16. Calculate the ratio of Category I equipment: EFCR = EFCN / ENS;

[0358] 17. Calculate the ratio of Category II equipment: ESCR = ESCN / ENS;

[0359] 18. Calculate the ratio of the three types of equipment: ETCR = ETCN / ENS;

[0360] 19. Calculate the ratio of key equipment: EMUR = EMUN / ENS;

[0361] 20. Calculate the general equipment ratio: EGUR = EGUN / ENS;

[0362] 21. Calculate the proportion of restricted equipment: ECUR = ECUN / ENS;

[0363] 22. Calculate the faulty equipment ratio: ENFR = ENF / ENS;

[0364] 23. Calculate the overhaul equipment ratio: ENDR = ENDM / ENS;

[0365] 24. Calculate the ratio of equipment under repair: ENIR = ENIM / ENS;

[0366] 25. Calculate the ratio of minor repair equipment: ENOR = ENOM / ENS;

[0367] 26. Calculate the ratio of other maintenance equipment: ENER = ENEM / ENS.

[0368] Spare parts inventory status: Various parameters of spare parts inventory status are calculated by mining the collected metadata. The specific mining and calculation methods are as follows:

[0369] The metadata involved include:

[0370] 1. The quantity of each spare part that needs to be put into storage each time: S_CHECKIN_N ij , the quantity of the jth type of spare parts entering the warehouse for the i-th time;

[0371] 2. Quantity of each spare part consumed each time: S_CHECKOUT_N ij , the quantity of the jth type of spare parts requested for the i-th time;

[0372] 3. Time for each spare part to be claimed: S_RQ_T ij , the time of the i-th request for the j-th spare part;

[0373] 4. Unit price of each spare part: SPV j ;

[0374] 5. Weight of each spare part: SPW j ;

[0375] 6. Spare parts number: SPN;

[0376] 7. Inventory standard for each spare part: SPIS j , the inventory standard of the jth spare part;

[0377] 8. Initial inventory of each spare part: SPIN j , the initial inventory quantity of the jth spare part.

[0378] The mining calculation process is as follows:

[0379] 1. Total consumption of each spare part: The total consumption quantity of the jth type of spare parts;

[0380] 2. Total number of each type of spare parts in storage: The total inventory quantity of the jth type of spare parts;

[0381] 3. Spare parts shortage ratio: SBR j =SIN j / SCN j , the out-of-stock ratio of the jth spare part;

[0382] 4. Spare parts inventory rate: SIR j =(SPIN j +SIN j -SCN j ) / SPIS j , the inventory rate of the jth spare part;

[0383] 5. Average spare parts shortage ratio:

[0384] 6. Average spare parts inventory rate:

[0385] 7. Total spare parts inventory quantity:

[0386] 8. Total spare parts inventory weight:

[0387] 9. Total value of spare parts in stock:

[0388] Total Motor Hour Reserve (EMHR): EMHR is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0389] The metadata involved include:

[0390] 1. Equipment overhaul period: EDMI, equipment overhaul interval (motorcycle hours);

[0391] 2. Equipment maintenance interval: EIMI, equipment maintenance interval (motorcycle hours);

[0392] 3. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0393] 4. Equipment establishment number: ENS.

[0394] The mining calculation process is as follows:

[0395] 1. Calculate the motorcycle hour reserve for each equipment: EMHR j

[0396] Case 1. EMHR j =EIMI-UMH j (UMH j <EIMI); Equipment j Motor hour reserve when instrument motor hours are less than the maintenance interval;

[0397] Case 2. EMHR j =EIMI-UMH j (EIMI≤UMH j <EDMI); Equipment j Motor hour reserve when instrument motor hours are greater than the maintenance interval;

[0398] 2. Calculate the total motorcycle hour reserve:

[0399] Total motorcycle hour consumption TEMH: TEMH is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0400] The metadata involved include:

[0401] 1. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0402] 2. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0403] 3. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0404] 4. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0405] 5. Equipment establishment number: ENS.

[0406] The mining calculation process is as follows:

[0407] 1. Time of use of each equipment: EUT ij =E_CC_IN ij -E_CC_OUT ij , the i-th use time of the j-th equipment; 2. Calculate the total motorcycle hour consumption:

[0408] Average Motor Hours (MEMH): MEMH is calculated by mining the collected metadata. The specific mining and calculation method is as follows:

[0409] The metadata involved include:

[0410] 1. Time for each equipment to return to the field: E_CC_IN ij , the i-th return time of the j-th equipment;

[0411] 2. Time each equipment is used each time: E_CC_OUT ij , the time when the jth equipment appears for the ith time;

[0412] 3. Initial motorcycle hours for each equipment: OMH j , the initial motor hours of the jth equipment;

[0413] 4. Each instrumented motorcycle hours: UMH j , the number of motorcycle hours used by the current instrument of the jth equipment;

[0414] 5. Equipment establishment number: ENS.

[0415] The mining calculation process is as follows:

[0416] 1. Time of use of each equipment: EUT ij=E_CC_IN ij -E_CC_OUT ij , the i-th usage time of the j-th equipment;

[0417] 2. Calculate the average motorcycle hour consumption:

[0418] The equipment quality improvement component can effectively discover quality defects in the design and production of equipment and its components by collecting and analyzing quality information during equipment use, such as components with high failure rates and their causes, components with long maintenance times, etc., thereby providing an important basis for continuous improvement and quality enhancement of equipment and laying the foundation for continuously improving the quality of equipment use. In addition, through the analysis of quality information, it can also help analyze the shortcomings in the equipment support system, such as important factors that lead to logistics delays, etc., to provide support for improving the level of equipment support capability building.

[0419] Embodiment 2:

[0420] like Figure 2 As shown, an embodiment of the present invention further provides an equipment quality information analysis device, comprising:

[0421] Acquisition module, used to obtain historical equipment quality information;

[0422] A construction module is used to build an equipment quality information analysis model based on deep learning according to historical equipment quality information;

[0423] The analysis module is used to input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

[0424] As an implementation of an embodiment of the present invention, the historical equipment quality information includes: basic equipment information, quality information generated during the equipment use process, quality information generated during the equipment maintenance process, and equipment material warehouse information.

[0425] As an implementation method of an embodiment of the present invention, the equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity and quality statistical analysis component, and equipment quality improvement component.

[0426] Embodiment 3:

[0427] The present invention also provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to implement the equipment quality information analysis method when executing the program stored in the memory.

[0428] Embodiment 4:

[0429] The present invention also provides a storage medium, wherein the storage medium stores machine executable instructions, and when the machine executable instructions are called and executed by a processor, the machine executable instructions can prompt the processor to implement the equipment quality information analysis method.

[0430] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for analyzing equipment quality information, characterized in that: The following steps are involved: Step S1, obtaining historical equipment quality information; Step S2: construct an equipment quality information analysis model based on deep learning according to historical equipment quality information; Step S3: input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

2. The equipment quality information analysis method according to claim 1, characterized in that: The historical equipment quality information includes: basic equipment information, quality information generated during the equipment use process, quality information generated during the equipment maintenance process, and equipment material warehouse information.

3. The equipment quality information analysis method according to claim 2, characterized in that: In step S2, the equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity and quality statistical analysis component, and equipment quality improvement component.

4. An equipment quality information analysis device, characterized in that: include: Acquisition module, used to obtain historical equipment quality information; A construction module is used to build an equipment quality information analysis model based on deep learning according to historical equipment quality information; The analysis module is used to input the equipment quality information to be processed into the equipment quality information analysis model to perform equipment quality management.

5. The equipment quality information analysis device according to claim 4, characterized in that: The historical equipment quality information includes: basic equipment information, quality information generated during the equipment use process, quality information generated during the equipment maintenance process, and equipment material warehouse information.

6. The equipment quality information analysis device according to claim 5, characterized in that: The equipment quality information analysis model includes: equipment reliability analysis component, equipment maintainability analysis component, equipment supportability analysis component, support resource inventory and consumption analysis component, equipment quantity and quality statistical analysis component, and equipment quality improvement component.

7. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to implement the equipment quality information analysis method described in any one of claims 1 to 3 when executing the program stored in the memory.

8. A storage medium, characterized in that: The storage medium stores machine executable instructions, and when the machine executable instructions are called and executed by the processor, the machine executable instructions prompt the processor to implement the equipment quality information analysis method according to any one of claims 1 to 3.

Images