Fixed-point maintenance supervision method and system based on multi-source data processing

Abstract

The invention relates to the technical field of fixed-point maintenance, and discloses a fixed-point maintenance supervision method and system based on multi-source data processing, and the method comprises the steps: obtaining historical multi-source maintenance data, constructing a fixed-point maintenance supervision model, obtaining real-time multi-source maintenance data, and obtaining a fixed-point maintenance supervision result based on multi-source data processing. The system corresponds to the method. According to the method, the historical multi-source maintenance data and the historical multi-source maintenance feature data are obtained, so that a data basis is provided for constructing the fixed-point maintenance supervision model; the maintenance process is supervised by using multi-source maintenance data by constructing a fixed-point maintenance supervision model; real-time multi-source maintenance data and real-time multi-source maintenance feature data are obtained to provide a data basis for obtaining fixed-point maintenance supervision, and output of a fixed-point maintenance supervision result is also realized; and real-time monitoring and accurate management of the maintenance process are also realized, and finally fixed-point maintenance supervision based on multi-source data processing is realized.

Description

Technical Field

[0001] The present application relates to the technical field of fixed-point maintenance, and specifically to a fixed-point maintenance supervision method and system based on multi-source data processing. Background Art

[0002] With the development of society, the demand for fixed-point maintenance of various insured objects is increasing, and the importance of maintenance management is becoming more and more prominent. Traditional maintenance supervision methods may have problems such as incomplete information and low management efficiency. Therefore, it is necessary to supervise fixed-point maintenance.

[0003] With the development of monitoring technology, punch card technology and item barcode technology, advanced data analysis technology is used to deeply mine the potential information in the data to achieve real-time monitoring and precise management of the maintenance process. It can not only detect abnormal conditions in maintenance in a timely manner, such as untimely maintenance and excessive maintenance, but also effectively evaluate the maintenance quality. In addition, based on the analysis results of multi-source data, it can provide a scientific basis for maintenance decisions, optimize the allocation of maintenance resources, improve maintenance efficiency and quality, and reduce maintenance costs. At the same time, this also helps to establish a complete maintenance file, provide strong support for the subsequent maintenance and management of equipment, and further improve the overall management level and service quality.

[0004] In summary, the prior art lacks a technical solution for fixed-point maintenance supervision based on multi-source data processing. Summary of the invention

[0005] The purpose of this application is to provide a fixed-point maintenance supervision method and system based on multi-source data processing to solve the technical problems raised in the above background technology.

[0006] To achieve the above objectives, this application discloses the following technical solutions:

[0007] In a first aspect, the present application discloses a method for fixed-point maintenance supervision based on multi-source data processing, the method comprising:

[0008] S1: Acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data;

[0009] S2: constructing a fixed-point maintenance supervision model using the multi-source historical maintenance feature data, wherein the fixed-point maintenance supervision model is used to supervise the maintenance process using the multi-source maintenance data;

[0010] S3: Acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data;

[0011] S4: Inputting the real-time multi-source maintenance data into the fixed-point maintenance model to obtain a fixed-point maintenance supervision result based on multi-source data processing.

[0012] By acquiring historical multi-source maintenance data and obtaining historical multi-source maintenance feature data, a data basis is provided for constructing a fixed-point maintenance supervision model; by constructing a fixed-point maintenance supervision model, the maintenance process is supervised using multi-source maintenance data; by acquiring real-time multi-source maintenance data and obtaining real-time multi-source maintenance feature data, a data basis is provided for obtaining fixed-point maintenance supervision, and the output of fixed-point maintenance supervision results is realized; real-time monitoring and precise management of the maintenance process is also realized.

[0013] Preferably, the historical multi-source maintenance data includes fault causes, maintenance content, maintenance time, maintenance manpower and maintenance parts.

[0014] Through the above, obtaining historical multi-source maintenance data provides a data basis for extracting maintenance features and a logical basis for fixed-point maintenance supervision.

[0015] Preferably, extracting maintenance features from the historical multi-source maintenance data to obtain the historical multi-source maintenance feature data specifically includes:

[0016] Extracting maintenance features from the fault causes, and consecutively numbering similar fault causes to obtain corresponding fault feature numbers F;

[0017] Extract maintenance features from the maintenance contents, and consecutively number similar maintenance contents to obtain corresponding content feature numbers C;

[0018] Extract maintenance features from the maintenance durations, and consecutively number similar maintenance durations to obtain corresponding duration feature numbers D;

[0019] Extract maintenance features from the maintenance workers, and consecutively number similar maintenance workers to obtain corresponding labor feature numbers A;

[0020] The maintenance features of the maintenance parts are extracted, and similar maintenance parts are numbered consecutively to obtain corresponding part feature numbers P.

[0021] Through the above, by extracting maintenance features and performing continuous numbering based on similarity, the rationality of the current fixed-point maintenance can be judged.

[0022] Preferably, the use of the multi-source historical maintenance feature data to construct a fixed-point maintenance supervision model specifically includes:

[0023] Construct a fault repair function, wherein the fault repair function is configured to output a corresponding content feature number, a duration feature number, a manual feature number, and a part feature number when the fault feature number is input; the fault repair function is expressed as:

[0024]

[0025] in, represents the fault repair function;

[0026] The fault repair function is stored in the fixed-point repair supervision model.

[0027] Through the above, the fault repair function realizes the prediction of content features, duration features, manual features and parts features based on fault characteristics, providing technical support for fixed-point maintenance supervision.

[0028] Preferably, the method of constructing a fixed-point maintenance supervision model using the multi-source historical maintenance feature data further includes:

[0029] The fixed-point maintenance supervision model includes a parts barcode library, a punch card reader and monitoring equipment, and generates corresponding parts data, manual punch card data and monitoring data;

[0030] Obtain the part data, the manual punching data and the monitoring data, and perform the following steps:

[0031] A1: Obtain the part feature code, and establish a part usage relationship between the part feature code and the part barcode in the part data;

[0032] A2: Acquire the manual feature code, and establish a manual usage relationship between the manual feature code and the manual punch-in record in the manual punch-in data;

[0033] A3: Obtain the duration feature number and the content feature number, and construct a duration usage relationship between the duration feature number and the content feature number and the monitoring records in the monitoring data based on a time series;

[0034] The parts usage relationship, the labor usage relationship and the time usage relationship are stored in the fixed-point maintenance supervision model.

[0035] Through the above, access to the parts barcode library, time recorder and monitoring equipment provides an accurate data basis for real-time multi-source maintenance data, and provides a data basis for the extraction of maintenance features of real-time multi-source maintenance data through parts usage relationship, manual usage relationship and time usage relationship.

[0036] Preferably, the real-time multi-source maintenance data includes real-time fault causes, real-time parts data, real-time manual clocking-in data and real-time monitoring data.

[0037] Through the above, real-time multi-source maintenance data provides a data basis for fixed-point maintenance.

[0038] Preferably, extracting maintenance features from the real-time multi-source maintenance data to obtain real-time multi-source maintenance feature data specifically includes:

[0039] Extract the maintenance feature of the real-time fault cause and obtain the corresponding real-time fault feature number F now ;

[0040] The maintenance feature of the real-time part data is extracted, and based on the part usage relationship, the corresponding real-time part feature number P is obtained. now ;

[0041] The maintenance feature is extracted from the real-time manual punch-in data, and based on the manual usage relationship, the corresponding real-time manual feature number A is obtained. now ;

[0042] The maintenance feature is extracted from the real-time monitoring data, and based on the time-use relationship, the corresponding real-time content feature number C is obtained. now and the real-time duration feature number D now .

[0043] Based on the above, the maintenance feature extraction of the real-time multi-source maintenance data provides a data basis for the fixed-point maintenance model.

[0044] Preferably, the step of inputting the real-time multi-source maintenance data into the fixed-point maintenance model specifically includes:

[0045] The real-time multi-source maintenance feature data is input into the fixed-point maintenance model, and the fault repair function is run based on the real-time fault feature number to obtain the corresponding predicted content feature number C predict , prediction duration feature number D predict , predict the artificial feature number A predict and predicted part feature number P predict .

[0046] Through the above, the predicted content feature number, predicted duration feature number, predicted labor feature number and predicted parts feature number are obtained to provide a data basis for judging the results of fixed-point maintenance supervision.

[0047] Preferably, obtaining the fixed-point maintenance supervision result based on multi-source data processing specifically includes the following steps:

[0048] Calculate the content difference ΔC=|C predict -C now |、Time difference ΔD=|D predict -D now |、Artificial difference ΔA=|A predict -A now | and part difference ΔP = |P predict -P now |;

[0049] Preset maintenance supervision index threshold I FMS_0 ;

[0050] The real-time fixed-point maintenance supervision index is calculated using the fixed-point maintenance supervision index formula, and the fixed-point maintenance supervision index formula is specifically:

[0051] I FMS =α1*ΔC+α2*ΔD+α3*ΔA+α4*ΔP

[0052] Among them, α1, α2, α3 and α4 are weight adjustment parameters, and α1+α2+α3+α4=1, I FMS The real-time fixed-point maintenance supervision indicator;

[0053] Judgment I FMS ≥I FMS_0 Is it true? If so, the real-time fixed-point maintenance supervision is output as abnormal, otherwise the real-time fixed-point maintenance supervision is output as normal.

[0054] Through the above, the calculation of content difference, time difference, labor difference and parts difference provides a data basis for calculating real-time fixed-point maintenance supervision indicators, and the fixed-point maintenance supervision indicators provide a judgment basis for real-time fixed-point maintenance supervision.

[0055] In a second aspect, the present application discloses a fixed-point maintenance supervision system based on multi-source data processing, the system is applicable to the fixed-point maintenance supervision method based on multi-source data processing as described in any one of the above items, and the system comprises:

[0056] The first data module, the historical data acquisition module is configured to: acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data;

[0057] A model building module, wherein the model building module is configured to: build a fixed-point maintenance supervision model using the multi-source historical maintenance feature data, wherein the fixed-point maintenance supervision model is used to supervise the maintenance process using the multi-source maintenance data;

[0058] A second data module, wherein the second data module is configured to: acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data;

[0059] The model operation module is configured to: input the real-time multi-source maintenance data into the fixed-point maintenance model to obtain a fixed-point maintenance supervision result based on multi-source data processing.

[0060] Beneficial effects: The fixed-point maintenance supervision method and system based on multi-source data processing of the present application, by acquiring historical multi-source maintenance data and obtaining historical multi-source maintenance feature data, provides a data basis for constructing a fixed-point maintenance supervision model; by constructing a fixed-point maintenance supervision model, it realizes the supervision of the maintenance process by using multi-source maintenance data; by acquiring real-time multi-source maintenance data and obtaining real-time multi-source maintenance feature data, it provides a data basis for obtaining fixed-point maintenance supervision, and also realizes the output of fixed-point maintenance supervision results; and also realizes real-time monitoring and precise management of the maintenance process. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 A flowchart of a method for fixed-point maintenance supervision based on multi-source data processing provided in an embodiment of the present application;

[0063] Figure 2 A schematic block diagram of a fixed-point maintenance supervision system based on multi-source data processing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0065] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0066] The first aspect of this embodiment discloses Figure 1 A fixed-point maintenance supervision method based on multi-source data processing is shown, the method comprising:

[0067] S1: Acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data;

[0068] S2: Use multi-source historical maintenance feature data to build a fixed-point maintenance supervision model, which is used to supervise the maintenance process using multi-source maintenance data;

[0069] S3: Acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data;

[0070] S4: Input the real-time multi-source maintenance data into the fixed-point maintenance model to obtain the fixed-point maintenance supervision results based on multi-source data processing.

[0071] By acquiring historical multi-source maintenance data and obtaining historical multi-source maintenance feature data, a data basis is provided for building a fixed-point maintenance supervision model; by building a fixed-point maintenance supervision model, the maintenance process is supervised using multi-source maintenance data; by acquiring real-time multi-source maintenance data and obtaining real-time multi-source maintenance feature data, a data basis is provided for obtaining fixed-point maintenance supervision, and the fixed-point maintenance supervision results are output;

[0072] Specifically, historical multi-source maintenance data includes failure causes, maintenance content, maintenance duration, maintenance labor, and maintenance parts.

[0073] Acquiring historical multi-source maintenance data provides a data basis for extracting maintenance features and a logical basis for fixed-point maintenance supervision.

[0074] Specifically, the maintenance feature extraction is performed on the historical multi-source maintenance data to obtain the historical multi-source maintenance feature data, which specifically includes:

[0075] Extract maintenance features from the fault causes, and consecutively number similar fault causes to obtain corresponding fault feature numbers F;

[0076] Extract maintenance features from maintenance contents, and consecutively number similar maintenance contents to obtain corresponding content feature numbers C;

[0077] Extract maintenance features from maintenance duration, and number similar maintenance durations consecutively to obtain corresponding duration feature numbers D;

[0078] Extract maintenance features from maintenance workers, and number similar maintenance workers consecutively to obtain corresponding labor feature numbers A;

[0079] The maintenance features of the maintenance parts are extracted, and similar maintenance parts are numbered consecutively to obtain the corresponding part feature number P.

[0080] By extracting maintenance features and assigning consecutive numbers based on similarity, the rationality of the current fixed-point maintenance can be judged.

[0081] Specifically, a fixed-point maintenance supervision model is constructed using multi-source historical maintenance feature data, including:

[0082] Construct a fault repair function, which is configured to output the corresponding content feature number, duration feature number, manual feature number and part feature number when the fault feature number is input; the fault repair function is expressed as:

[0083]

[0084] in, represents the fault repair function;

[0085] The fault repair function is stored in the fixed-point maintenance supervision model.

[0086] The fault repair function enables the prediction of content features, duration features, manual features and parts features based on fault characteristics, providing technical support for fixed-point maintenance supervision.

[0087] Specifically, the fixed-point maintenance supervision model is constructed using multi-source historical maintenance feature data, which also includes:

[0088] The fixed-point maintenance supervision model includes a parts barcode library, a punch card reader and monitoring equipment, and generates corresponding parts data, manual punch card data and monitoring data;

[0089] Obtain part data, manual punching data, and monitoring data, and perform the following steps:

[0090] A1: Get the part feature code and establish a part usage relationship between the part feature code and the part barcode in the part data;

[0091] A2: Obtain the manual feature code and establish a manual usage relationship between the manual feature code and the manual punch-in record in the manual punch-in data;

[0092] A3: Obtain the duration feature number and the content feature number, and build a duration usage relationship based on the time series by comparing the duration feature number and the content feature number with the monitoring records in the monitoring data;

[0093] The parts usage relationship, labor usage relationship and time usage relationship are stored in the fixed-point maintenance supervision model.

[0094] Access to the parts barcode library, time recorder and monitoring equipment provides an accurate data basis for real-time multi-source maintenance data, and provides a data basis for extracting maintenance features from real-time multi-source maintenance data through parts usage relationships, manual usage relationships and time usage relationships.

[0095] Specifically, real-time multi-source maintenance data includes real-time fault causes, real-time parts data, real-time manual clocking-in data, and real-time monitoring data.

[0096] Real-time multi-source maintenance data provides a data basis for fixed-point maintenance.

[0097] Specifically, the maintenance feature extraction is performed on the real-time multi-source maintenance data to obtain the real-time multi-source maintenance feature data, which specifically includes:

[0098] Extract maintenance features of real-time fault causes and obtain corresponding real-time fault feature numbers F now ;

[0099] Extract maintenance features from real-time parts data and obtain the corresponding real-time part feature number P based on the parts usage relationship. now ;

[0100] Extract maintenance features from real-time manual punch-in data, and obtain the corresponding real-time manual feature number A based on the manual usage relationship now ;

[0101] The maintenance feature is extracted from the real-time monitoring data, and the corresponding real-time content feature number C is obtained based on the time-use relationship. now and real-time duration feature number D now .

[0102] By extracting maintenance features from real-time multi-source maintenance data, a data basis is provided for the fixed-point maintenance model.

[0103] Specifically, real-time multi-source maintenance data is input into the fixed-point maintenance model, including:

[0104] The real-time multi-source maintenance feature data is input into the fixed-point maintenance model, and the corresponding prediction content feature number C is obtained based on the real-time fault feature number and running the fault maintenance function. predict , prediction duration feature number D predict , predict the artificial feature number A predict and predicted part feature number P predict .

[0105] Obtaining the predicted content feature number, predicted duration feature number, predicted labor feature number and predicted parts feature number provides a data basis for judging the results of fixed-point maintenance supervision.

[0106] Specifically, obtaining the fixed-point maintenance supervision results based on multi-source data processing includes the following steps:

[0107] Calculate the content difference ΔC=|C predict -C now |、Time difference ΔD=|D predict -D now |、Artificial difference ΔA=|A predict -A now | and part difference ΔP = |P predict -P now |;

[0108] Preset maintenance supervision index threshold I FMS_0 ;

[0109] The real-time fixed-point maintenance supervision index is calculated using the fixed-point maintenance supervision index formula. The fixed-point maintenance supervision index formula is as follows:

[0110] I FMS =α1*ΔC+α2*ΔD+α3*ΔA+α4*ΔP

[0111] Among them, α1, α2, α3 and α4 are weight adjustment parameters, and α1+α2+α3+α4=1, I FMS To provide real-time fixed-point maintenance supervision indicators;

[0112] Judgment I FMS ≥I FMS_0 Is it true? If so, the real-time fixed-point maintenance supervision is output as abnormal, otherwise the real-time fixed-point maintenance supervision is output as normal.

[0113] By calculating the content difference, time difference, labor difference and parts difference, a data basis is provided for calculating the real-time fixed-point maintenance supervision indicators. The fixed-point maintenance supervision indicators provide a basis for judgment for real-time fixed-point maintenance supervision.

[0114] The second aspect of this embodiment discloses Figure 2A fixed-point maintenance supervision system based on multi-source data processing is shown, and the system is applicable to any of the above fixed-point maintenance supervision methods based on multi-source data processing, and the system includes:

[0115] The first data module, the historical data acquisition module is configured to: acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data;

[0116] A model building module, the model building module is configured to: build a fixed-point maintenance supervision model using multi-source historical maintenance feature data, the fixed-point maintenance supervision model is used to supervise the maintenance process using multi-source maintenance data;

[0117] The second data module is configured to: acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data;

[0118] The model operation module is configured to: input real-time multi-source maintenance data into the fixed-point maintenance model to obtain the fixed-point maintenance supervision results based on multi-source data processing.

[0119] In summary, the fixed-point maintenance supervision method and system based on multi-source data processing of this embodiment provides a data basis for constructing a fixed-point maintenance supervision model by acquiring historical multi-source maintenance data and obtaining historical multi-source maintenance feature data; realizes supervision of the maintenance process by utilizing multi-source maintenance data by constructing a fixed-point maintenance supervision model; provides a data basis for obtaining fixed-point maintenance supervision by acquiring real-time multi-source maintenance data and obtaining real-time multi-source maintenance feature data, and also realizes output of fixed-point maintenance supervision results; and also realizes real-time monitoring and precise management of the maintenance process.

[0120] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0121] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A fixed-point maintenance supervision method based on multi-source data processing, It is characterized in that The method includes: S1: Acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data; S2: constructing a fixed-point maintenance supervision model using the multi-source historical maintenance feature data, wherein the fixed-point maintenance supervision model is used to supervise the maintenance process using the multi-source maintenance data; S3: Acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data; S4: Inputting the real-time multi-source maintenance data into the fixed-point maintenance model to obtain a fixed-point maintenance supervision result based on multi-source data processing.

2. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 1, It is characterized in that The historical multi-source maintenance data includes fault causes, maintenance content, maintenance time, maintenance labor and maintenance parts.

3. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 2, It is characterized in that The extracting maintenance features from the historical multi-source maintenance data to obtain the historical multi-source maintenance feature data specifically includes: Extracting maintenance features from the fault causes, and consecutively numbering similar fault causes to obtain corresponding fault feature numbers F; Extract maintenance features from the maintenance contents, and consecutively number similar maintenance contents to obtain corresponding content feature numbers C; Extract maintenance features from the maintenance durations, and consecutively number similar maintenance durations to obtain corresponding duration feature numbers D; Extract maintenance features from the maintenance workers, and consecutively number similar maintenance workers to obtain corresponding labor feature numbers A; The maintenance features of the maintenance parts are extracted, and similar maintenance parts are numbered consecutively to obtain corresponding part feature numbers P.

4. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 3, It is characterized in that The method of constructing a fixed-point maintenance supervision model by using the multi-source historical maintenance feature data specifically includes: Construct a fault repair function, wherein the fault repair function is configured to output a corresponding content feature number, a duration feature number, a manual feature number, and a part feature number when the fault feature number is input; the fault repair function is expressed as: in, represents the fault repair function; The fault repair function is stored in the fixed-point repair supervision model.

5. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 4, It is characterized in that The method of constructing a fixed-point maintenance supervision model using the multi-source historical maintenance feature data further includes: The fixed-point maintenance supervision model includes a parts barcode library, a punch card reader and monitoring equipment, and generates corresponding parts data, manual punch card data and monitoring data; Obtain the part data, the manual punching data and the monitoring data, and perform the following steps: A1: Obtain the part feature code, and establish a part usage relationship between the part feature code and the part barcode in the part data; A2: Acquire the manual feature code, and establish a manual usage relationship between the manual feature code and the manual punch-in record in the manual punch-in data; A3: Obtain the duration feature number and the content feature number, and construct a duration usage relationship between the duration feature number and the content feature number and the monitoring records in the monitoring data based on a time series; The parts usage relationship, the labor usage relationship and the time usage relationship are stored in the fixed-point maintenance supervision model.

6. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 5, It is characterized in that The real-time multi-source maintenance data includes real-time fault causes, real-time parts data, real-time manual punch-in data and real-time monitoring data.

7. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 6, It is characterized in that The extracting maintenance features from the real-time multi-source maintenance data to obtain the real-time multi-source maintenance feature data specifically includes: Extract the maintenance feature of the real-time fault cause and obtain the corresponding real-time fault feature number F now ; The maintenance feature of the real-time part data is extracted, and based on the part usage relationship, the corresponding real-time part feature number P is obtained. now ; The maintenance feature is extracted from the real-time manual punch-in data, and based on the manual usage relationship, the corresponding real-time manual feature number A is obtained. now ; The maintenance feature is extracted from the real-time monitoring data, and based on the time-use relationship, the corresponding real-time content feature number C is obtained. now and the real-time duration feature number D now .

8. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 7, It is characterized in that The step of inputting the real-time multi-source maintenance data into the fixed-point maintenance model specifically includes: The real-time multi-source maintenance feature data is input into the fixed-point maintenance model, and the fault repair function is run based on the real-time fault feature number to obtain the corresponding predicted content feature number C predict , prediction duration feature number D predict , predict the artificial feature number A predict and predicted part feature number P predict .

9. The method for fixed-point maintenance supervision based on multi-source data processing according to claim 8, It is characterized in that The method of obtaining the fixed-point maintenance supervision result based on multi-source data processing specifically includes the following steps: Calculate the content difference ΔC=|C predict -C now |、Duration difference ΔD=|D predict -D now |、Artificial difference ΔA=|A predict -A now | and part difference ΔP = |P predict -P now |; Preset maintenance supervision index threshold I FMS_0 ; The real-time fixed-point maintenance supervision index is calculated using the fixed-point maintenance supervision index formula, and the fixed-point maintenance supervision index formula is specifically: I FMS =a 1 *ΔC+a 2 *ΔD+a 3 *ΔA+a 4 *ΔP Among them, α 1 , α 2 , α 3 and α 4 is the weight adjustment parameter, and α 1 +α 2 +α 3 +α 4 =1,I FMS The real-time fixed-point maintenance supervision indicator; Judgment I FMS ≥I FMS_0 Is it true? If so, the real-time fixed-point maintenance supervision is output as abnormal, otherwise the real-time fixed-point maintenance supervision is output as normal.

10. A fixed-point maintenance supervision system based on multi-source data processing, the system being applicable to the fixed-point maintenance supervision method based on multi-source data processing as claimed in any one of claims 1 to 9, It is characterized in that The system includes: The first data module, the historical data acquisition module is configured to: acquire historical multi-source maintenance data, extract maintenance features from the historical multi-source maintenance data, and obtain historical multi-source maintenance feature data; A model building module, wherein the model building module is configured to: build a fixed-point maintenance supervision model using the multi-source historical maintenance feature data, wherein the fixed-point maintenance supervision model is used to supervise the maintenance process using the multi-source maintenance data; A second data module, wherein the second data module is configured to: acquire real-time multi-source maintenance data, extract maintenance features from the real-time multi-source maintenance data, and obtain real-time multi-source maintenance feature data; The model operation module is configured to: input the real-time multi-source maintenance data into the fixed-point maintenance model to obtain a fixed-point maintenance supervision result based on multi-source data processing.

Images