A device data supervision method and system based on big data

Abstract

The present invention relates to the field of big data technology, and specifically to a method and system for monitoring equipment data based on big data. The system comprises an equipment data analysis module, a comprehensive fault risk analysis module, an external fault risk analysis module and an equipment data rationalization analysis module. The comprehensive fault risk analysis module is used to analyze product manufacturing data of corresponding links of the manufacturing process of products to be mass-produced based on the working status of product quality inspection and early warning devices in the factory area to be monitored, and predict the comprehensive fault risk of finished products in combination with the manufacturing data of products in corresponding links. The present invention analyzes the test data of corresponding products to be mass-produced in the factory area to be monitored, determines the cause of the failure of the corresponding products to be mass-produced according to the test data of each link, and generates an early warning signal based on the corresponding cause of the failure, thereby not only improving the maintenance efficiency of the products to be mass-produced, but also being able to effectively trace the cause of the problem, so that the mass production of the products to be mass-produced is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a device data supervision method and system based on big data. Background Art

[0002] With the continuous development of science and technology, the vigorous development of the Internet of Things, big data, cloud computing, etc., the continuous improvement of data twin projects, equipment operation and maintenance, and warehouse transportation monitoring systems, the requirements for the supervision of equipment systems are getting higher and higher. At present, with the rapid development of the manufacturing industry, with the problems of equipment diversity and quantity, the backward supervision has led to the inability of many factories to combine the big data of the products to be mass-produced with the causes of the problems for visual monitoring. The troubleshooting of the products to be mass-produced still requires a large number of manpower and a lot of time to conduct secondary quality inspections at various production links, and it is impossible to efficiently manage the equipment production data; the traditional data traceability supervision mode for products to be mass-produced has certain defects, such as delayed feedback of fault location information and poor visualization traceability of production data of products to be mass-produced. Therefore, a method and system for equipment data supervision based on big data is needed. Summary of the invention

[0003] The purpose of the present invention is to provide a device data supervision method and system based on big data to solve the problems raised in the above background technology. The present invention provides the following technical solutions:

[0004] A device data supervision method based on big data, the method comprising the following steps:

[0005] S1. Obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation;

[0006] S2. Based on the working status of the product quality inspection and early warning device in the factory area to be monitored, analyze the product manufacturing data of the corresponding links of the manufacturing process of the products to be mass-produced, and predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links;

[0007] S3. Analyze the external failure risk generated in the assembly and testing process of the corresponding products to be mass-produced based on the working status of the product quality inspection and early warning devices in the factory area to be monitored;

[0008] S4. Based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, judge the rationality of product mass production, and generate early warning signals based on the judgment results.

[0009] Furthermore, the method in S1 comprises the following steps:

[0010] Step 1001: Obtain a test report of any type of mass-produced product in the factory area to be monitored, and record the test report of the a-th type of mass-produced product as set A. a The test report consists of test data corresponding to one or more test items, wherein the data in the test report is a preset value of the database, which is collected based on the data tested in the corresponding product quality inspection link.

[0011]

[0012] in It indicates the test report of the test product numbered n among the products to be mass-produced in the a-th category of the factory area to be monitored, where n indicates the maximum number of the test product among the corresponding products to be mass-produced in the factory area to be monitored;

[0013] Step 1002: Based on the analysis results in step 1001, theoretical analysis values ​​of the detection data of various types of mass-produced products in the factory area to be monitored are obtained, which are recorded as set B.

[0014] B=(B1,B2,B3,B a , ..., B m ),

[0015] Among them B a represents the theoretical analysis report of the detection data of the a-th type of mass-produced products in the monitored factory area, m represents the number of types of mass-produced output in the monitored factory area, and the theoretical analysis report represents the theoretical value designed for the corresponding link in the plan formulated before the production of the corresponding product;

[0016] Step 1003: Based on the analysis results of step 1001 and step 1002, determine the degree of deviation of the test data of each product to be mass-produced in the factory area to be monitored, and record the degree of deviation of the test data of the test product numbered b in the a-th category of products to be mass-produced in the factory area to be monitored as where b∈[1,n],

[0017]

[0018] Where β represents the proportionality coefficient, which is a preset value in the database; α i Indicates the proportionality coefficient of the corresponding data in the test report, and the proportionality coefficient is a preset value in the database; It represents the test data value corresponding to the i-th test item in the test report of the test product numbered b in the a-th type of mass-produced product in the factory area to be monitored; Z i (B a) represents the theoretical analysis value corresponding to the i-th test item in the theoretical analysis report of the test data of the a-th type of mass-produced products in the factory area to be monitored; j represents the total number of test items in the test report of the corresponding mass-produced products in the factory area to be monitored;

[0019] Step 1004, looping step 1003 to obtain the degree of deviation of the test data of the corresponding test product in the product to be mass-produced in the factory area to be monitored, and further analyzing the comprehensive deviation degree value of the corresponding product to be mass-produced in combination with the degree of deviation of the test data of the corresponding test product,

[0020] With point o as the origin, the number of the test product as the x-axis, and the degree of deviation of the test data of the corresponding test product as the y-axis, a first plane rectangular coordinate system is constructed.

[0021] In the first plane rectangular coordinate system, the coordinate points corresponding to the deviation degree of the test data of the test products corresponding to each serial number of the products to be mass-produced in category a are marked, and two adjacent coordinate points are connected in sequence to generate a fitting curve, which is recorded as N1(x).

[0022] Based on the theoretical analysis value of the detection data of various types of mass-produced products in the factory area to be monitored, the maximum value of the standard deviation interval of the corresponding products to be mass-produced is obtained. In the first plane rectangular coordinate system, the coordinate point corresponding to the maximum value of the standard deviation interval of the a-th type of products to be mass-produced is marked, and a straight line parallel to the x-axis is constructed through the marked point, recorded as N2(x), then the comprehensive deviation degree value of the a-th type of products to be mass-produced in the factory area to be monitored is ZP a , where the standard deviation interval is a preset value, indicating the fluctuation range of the theoretical value of the monitoring data of the corresponding product to be mass-produced.

[0023]

[0024] Wherein γ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database;

[0025] Step 1005: Based on the analysis result of step 1004, an early warning signal is generated according to the comprehensive deviation degree value of the corresponding product to be mass-produced.

[0026] If ZP a ≤ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is within the standard deviation range, and no warning signal is issued.

[0027] If ZP a >ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is not within the standard deviation range, and a warning signal is issued;

[0028] Step 1006, looping steps 1003 to 1005 to obtain the products to be mass-produced whose comprehensive deviation values ​​of various types of products to be mass-produced in the monitored factory area are not within the standard deviation range, and record the products to be mass-produced in table M1.

[0029] The present invention obtains the inspection report of the corresponding product to be mass-produced in the factory area to be monitored, calculates the deviation based on the data in the inspection report and the preset theoretical analysis value, and judges whether there is a production problem in the process of the product to be mass-produced based on the deviation calculation result, thereby providing data reference for subsequent tracing back to the cause of the process manufacturing problem of the corresponding product to be mass-produced.

[0030] Furthermore, the method in S2 comprises the following steps:

[0031] Step 2001: Based on the analysis results of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the product manufacturing data of the corresponding links of the manufacturing process of the c-th type of products to be mass-produced, which is recorded as set C. c ,

[0032]

[0033] in represents the product manufacturing data of the corresponding link in the kth manufacturing process of the cth type of mass-produced product in the factory area to be monitored, where k represents the total number of manufacturing processes of the corresponding mass-produced product in the factory area to be monitored;

[0034] Step 2002: Based on the analysis results of step 2001, the feasibility of manufacturing data of two adjacent links of the manufacturing process of the c-th type of products to be mass-produced is evaluated in turn, which is recorded as Feasibility c ,

[0035]

[0036] Where τ represents the proportionality coefficient, which is a preset value in the database. It represents the product manufacturing data error status value of the u-th link of the c-th type of mass-produced product in the factory area to be monitored, represents the product manufacturing data error state value of the u+1th link of the cth type of mass-produced product in the factory area to be monitored, and the error state value is read by the detection equipment, H[] represents the conditional judgment function, H1[] represents the first judgment function,

[0037] like Within the preset range,

[0038] like Within the preset range,

[0039] like but

[0040] like or but

[0041] Step 2003: Based on the analysis result of step 2002, predict the comprehensive fault risk of the corresponding mass-produced product, and record the comprehensive fault risk of the c-th type of mass-produced product as Fault c ,

[0042] Fault c =-σ·Feasibility c ,

[0043] Wherein σ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database;

[0044] Step 2004, looping steps 2001 to 2003 to obtain the comprehensive failure risk situation of each product to be mass-produced in the factory area to be monitored, and recording the failure risk situation in table M2.

[0045] The present invention extracts product manufacturing data of corresponding links in the manufacturing process of products to be mass-produced with unqualified deviation calculation in the factory area to be monitored, combines the manufacturing data of products in corresponding links with the manufacturing data of products in corresponding links to predict the comprehensive failure risk situation of finished products, and judges whether there are problems in the manufacturing links that affect the product process manufacturing requirements based on the comprehensive failure risk situation, thereby providing data reference for subsequent tracing of manufacturing process problems of products to be mass-produced.

[0046] Furthermore, the method in S3 comprises the following steps:

[0047] Step 3001: Based on the analysis result of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the data corresponding to the assembly test link of the c-th type of products to be mass-produced, which is recorded as set D c ,

[0048]

[0049] in represents the Lth data in the assembly and testing link of the cth type of mass-produced product in the factory area to be monitored, and L represents the total number of data in the assembly and testing link of the corresponding mass-produced product in the factory area to be monitored;

[0050] Step 3002: Based on the analysis results of step 3001, analyze the external fault risk generated in the assembly and testing phase of the corresponding mass-produced products, and record the external fault risk generated in the assembly and testing phase of the c-th mass-produced products in the monitored factory area as Faultout. c ,

[0051] Faultout c =P(working c )·Vibrate c ,

[0052] Among them working c represents the working status result of the test operation of the c-th type of mass-produced product in the monitored factory, and the working status result is known through the working status indicator light, P() represents the second judgment function,

[0053] If the working status indicator light is on, then P c )=1, if the working status indicator light is off, then P(working c )=0,

[0054] Vibrate c Indicates the data value corresponding to the vibration test link of the C-type mass-produced product in the monitored factory, and the data value corresponding to the vibration test link is obtained by monitoring the impact sound between the various parts of the corresponding mass-produced product by the corresponding equipment;

[0055] Step 3003, loop step 3002 to obtain the external failure risk situation of each assembly and test link of the mass-produced products in the factory area to be monitored, and record the failure risk situation in table M3.

[0056] The present invention obtains a data analysis report on the assembly and testing link of the corresponding product to be mass-produced, and combines the corresponding data in the data analysis report to determine whether there is a problem in the assembly link of the current product to be mass-produced, thereby providing a data reference for determining whether the product to be mass-produced can be mass-produced.

[0057] Furthermore, the method in S4 comprises the following steps:

[0058] Step 4001: Obtain the test results of the manufacturing and assembly stages of the current product to be mass-produced, and analyze the rationality of the current product to be mass-produced based on the analysis method of step 2003 and step 3002, which is recorded as Produce now ,

[0059] Produce now =F(Fault now ∩M2)+F(Faultout now ∩M3),

[0060] Wherein F() represents the third judgment function; now represents the type of product to be mass-produced;

[0061] like Then F(Fault now ∩M2)=0; if Then F(Fault now ∩M2)=1;

[0062] like Then F(Faultout now ∩M3)=0; if Then F(Faultout now ∩M3)=1;

[0063] Step 4002: Generate an early warning signal based on the analysis result of step 4001.

[0064] If Produce now =0, no warning signal is issued.

[0065] If Produce now =1, a Level II warning signal is issued.

[0066] If Produce now =2, a Level I warning signal is issued;

[0067] Step 4003, based on the analysis results of step 4002, notify the relevant staff to perform maintenance operations. When the system identifies a Level II warning signal, notify the relevant staff to perform maintenance on the corresponding links based on the rationality of the products to be mass-produced. When the system identifies a Level I warning signal, notify the relevant staff to perform maintenance on each link of the corresponding products to be mass-produced. When the system does not identify a warning signal, the corresponding products to be mass-produced will be processed for mass production.

[0068] A device data supervision system based on big data, the system includes the following modules:

[0069] Equipment data analysis module: The equipment data analysis module is used to obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation;

[0070] Comprehensive failure risk analysis module: The comprehensive failure risk analysis module is used to analyze the product manufacturing data of the corresponding links of the manufacturing process of the mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored, and to predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links;

[0071] External fault risk analysis module: The external fault risk analysis module is used to analyze the external fault risk situation generated in the assembly and testing link of the corresponding mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored;

[0072] Equipment data rationalization analysis module: The equipment data rationalization analysis module is used to judge the rationality of product mass production based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, and generate early warning signals based on the judgment results.

[0073] Furthermore, the equipment data analysis module includes a data acquisition unit, a deviation analysis unit and a product category classification unit:

[0074] The data acquisition unit is used to obtain the detection report of the corresponding product to be mass-produced in the factory area to be monitored;

[0075] The deviation analysis unit is used to calculate the deviation between the data in the test report of the corresponding product to be mass-produced in the factory area to be monitored and the corresponding theoretical analysis data based on the analysis result of the data acquisition unit;

[0076] The product category classification unit is used to generate an early warning signal based on the analysis result of the deviation analysis unit and the deviation calculation result of the corresponding product to be mass-produced, and classify the products to be mass-produced in the monitored factory area according to the early warning signal.

[0077] Furthermore, the comprehensive fault risk analysis module includes a manufacturing data feasibility analysis unit, a comprehensive fault risk analysis unit and a data recording unit:

[0078] The manufacturing data feasibility analysis unit is used to analyze the manufacturing data feasibility of products in two adjacent links in the manufacturing process of the corresponding product to be mass-produced in the factory area to be monitored;

[0079] The comprehensive failure risk analysis unit is used to calculate the comprehensive failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the manufacturing data feasibility analysis unit;

[0080] The data recording unit is used to record the analysis result of the comprehensive fault analysis unit in real time.

[0081] Furthermore, the external fault risk analysis module includes an assembly test data acquisition unit and an external fault risk analysis unit:

[0082] The assembly test data acquisition unit is used to acquire the data report of the assembly quality inspection link of the corresponding product to be mass-produced;

[0083] The external failure risk analysis unit is used to further analyze the external failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the assembly test data acquisition unit.

[0084] Furthermore, the equipment data rationalization analysis module includes a product rationality analysis unit, a warning condition signal generation unit and a warning signal elimination unit:

[0085] The product rationality analysis unit is used to calculate the rationality by combining the test results of the manufacturing link and the assembly link of the corresponding product to be mass-produced;

[0086] The early warning condition signal generating unit is used to generate an early warning condition signal according to the analysis result of the product rationality analyzing unit;

[0087] The early warning signal cancellation unit is used to take corresponding measures to cancel the warning in combination with the analysis result of the early warning condition signal generation unit.

[0088] The present invention analyzes the test data of the corresponding products to be mass-produced in the factory area to be monitored, determines the cause of the failure of the corresponding products to be mass-produced according to the test data of each link, and generates an early warning signal based on the corresponding cause of the failure, thereby not only improving the maintenance efficiency of the products to be mass-produced, but also effectively tracing the cause of the problem, so that the batch production of the products to be mass-produced is effectively guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a flow chart of a device data supervision method based on big data of the present invention;

[0090] Figure 2 It is a module schematic diagram of a device data supervision system based on big data of the present invention. DETAILED DESCRIPTION

[0091] 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.

[0092] Example 1: Please refer to Figure 1 , in this embodiment:

[0093] A device data supervision method based on big data, the method comprising the following steps:

[0094] S1. Obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation;

[0095] The method in S1 comprises the following steps:

[0096] Step 1001: Obtain a test report of any type of mass-produced product in the factory area to be monitored, and record the test report of the a-th type of mass-produced product as set A. a The test report consists of test data corresponding to one or more test items.

[0097]

[0098] in It indicates the test report of the test product numbered n among the products to be mass-produced in the a-th category of the factory area to be monitored, where n indicates the maximum number of the test product among the corresponding products to be mass-produced in the factory area to be monitored;

[0099] Step 1002: Based on the analysis results in step 1001, theoretical analysis values ​​of the detection data of various types of mass-produced products in the factory area to be monitored are obtained, which are recorded as set B.

[0100] B=(B1,B2,B3,B a , ..., B m ),

[0101] Among them B a represents the theoretical analysis report of the detection data of the a-th type of products to be mass-produced in the factory area to be monitored, and m represents the number of types of output to be mass-produced in the factory area to be monitored;

[0102] Step 1003: Based on the analysis results of step 1001 and step 1002, determine the degree of deviation of the test data of each product to be mass-produced in the factory area to be monitored, and record the degree of deviation of the test data of the test product numbered b in the a-th category of products to be mass-produced in the factory area to be monitored as where b∈[1,n],

[0103]

[0104] Where β represents the proportionality coefficient, which is a preset value in the database; α i Indicates the proportionality coefficient of the corresponding data in the test report, and the proportionality coefficient is a preset value in the database; It represents the test data value corresponding to the i-th test item in the test report of the test product numbered b in the a-th type of mass-produced product in the factory area to be monitored; Z i (B a ) represents the theoretical analysis value corresponding to the i-th test item in the theoretical analysis report of the test data of the a-th type of mass-produced products in the factory area to be monitored; j represents the total number of test items in the test report of the corresponding mass-produced products in the factory area to be monitored;

[0105] Step 1004, looping step 1003 to obtain the degree of deviation of the test data of the corresponding test product in the product to be mass-produced in the factory area to be monitored, and further analyzing the comprehensive deviation degree value of the corresponding product to be mass-produced in combination with the degree of deviation of the test data of the corresponding test product,

[0106] With point o as the origin, the number of the test product as the x-axis, and the degree of deviation of the test data of the corresponding test product as the y-axis, a first plane rectangular coordinate system is constructed.

[0107] In the first plane rectangular coordinate system, the coordinate points corresponding to the deviation degree of the test data of the test products corresponding to each serial number of the products to be mass-produced in category a are marked, and two adjacent coordinate points are connected in sequence to generate a fitting curve, which is recorded as N1(x).

[0108] Based on the theoretical analysis value of the detection data of various types of mass-produced products in the factory area to be monitored, the maximum value of the standard deviation interval of the corresponding products to be mass-produced is obtained. In the first plane rectangular coordinate system, the coordinate point corresponding to the maximum value of the standard deviation interval of the a-th type of products to be mass-produced is marked, and a straight line parallel to the x-axis is constructed through the marked point, recorded as N2(x), then the comprehensive deviation degree value of the a-th type of products to be mass-produced in the factory area to be monitored is ZP a ,

[0109]

[0110] Wherein γ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database;

[0111] Step 1005: Based on the analysis result of step 1004, an early warning signal is generated according to the comprehensive deviation degree value of the corresponding product to be mass-produced.

[0112] If ZP a ≤ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is within the standard deviation range, and no warning signal is issued.

[0113] If ZP a >ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is not within the standard deviation range, and a warning signal is issued;

[0114] Step 1006, looping steps 1003 to 1005 to obtain the products to be mass-produced whose comprehensive deviation values ​​of various types of products to be mass-produced in the monitored factory area are not within the standard deviation range, and record the products to be mass-produced in table M1.

[0115] S2. Based on the working status of the product quality inspection and early warning device in the factory area to be monitored, analyze the product manufacturing data of the corresponding links of the manufacturing process of the products to be mass-produced, and predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links;

[0116] The method in S2 comprises the following steps:

[0117] Step 2001: Based on the analysis results of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the product manufacturing data of the corresponding links of the manufacturing process of the c-th type of products to be mass-produced, which is recorded as set C. c ,

[0118]

[0119] in represents the product manufacturing data of the corresponding link in the kth manufacturing process of the cth type of mass-produced product in the factory area to be monitored, where k represents the total number of manufacturing processes of the corresponding mass-produced product in the factory area to be monitored;

[0120] Step 2002: Based on the analysis results of step 2001, the feasibility of manufacturing data of two adjacent links of the manufacturing process of the c-th type of products to be mass-produced is evaluated in turn, which is recorded as Feasibility c ,

[0121]

[0122] Where τ represents the proportionality coefficient, which is a preset value in the database. It represents the product manufacturing data error status value of the u-th link of the c-th type of mass-produced product in the factory area to be monitored, represents the product manufacturing data error state value of the u+1th link of the cth type of mass-produced product in the factory area to be monitored, and the error state value is read by the detection equipment, H[] represents the conditional judgment function, H1[] represents the first judgment function,

[0123] like Within the preset range,

[0124] like Within the preset range,

[0125] like but

[0126] like or but

[0127] Step 2003: Based on the analysis result of step 2002, predict the comprehensive fault risk of the corresponding mass-produced product, and record the comprehensive fault risk of the c-th type of mass-produced product as Faultc ,

[0128] Fault c =-σ·Feasibility c ,

[0129] Wherein σ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database;

[0130] Step 2004, looping steps 2001 to 2003 to obtain the comprehensive failure risk situation of each product to be mass-produced in the factory area to be monitored, and recording the failure risk situation in table M2.

[0131] S3. Analyze the external failure risk generated in the assembly and testing process of the corresponding products to be mass-produced based on the working status of the product quality inspection and early warning devices in the factory area to be monitored;

[0132] The method in S3 comprises the following steps:

[0133] Step 3001: Based on the analysis result of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the data corresponding to the assembly test link of the c-th type of products to be mass-produced, which is recorded as set D c ,

[0134]

[0135] in represents the Lth data in the assembly and testing link of the cth type of mass-produced product in the factory area to be monitored, and L represents the total number of data in the assembly and testing link of the corresponding mass-produced product in the factory area to be monitored;

[0136] Step 3002: Based on the analysis results of step 3001, analyze the external fault risk generated in the assembly and testing phase of the corresponding mass-produced products, and record the external fault risk generated in the assembly and testing phase of the c-th mass-produced products in the monitored factory area as Faultout. c ,

[0137] Faultout c =P(working c )·Vibrate c ,

[0138] Among them working c represents the working status result of the test operation of the c-th type of mass-produced product in the monitored factory, and the working status result is known through the working status indicator light, P() represents the second judgment function,

[0139] If the working status indicator light is on, then P c )=1, if the working status indicator light is off, then P(working c )=0,

[0140] Vibrate c Indicates the data value corresponding to the vibration test link of the C-type mass-produced product in the monitored factory, and the data value corresponding to the vibration test link is obtained by monitoring the impact sound between the various parts of the corresponding mass-produced product by the corresponding equipment;

[0141] Step 3003, loop step 3002 to obtain the external failure risk situation of each assembly and test link of the mass-produced products in the factory area to be monitored, and record the failure risk situation in table M3.

[0142] S4. Based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, judge the rationality of product mass production, and generate early warning signals based on the judgment results.

[0143] The method in S4 comprises the following steps:

[0144] Step 4001: Obtain the test results of the manufacturing and assembly stages of the current product to be mass-produced, and analyze the rationality of the current product to be mass-produced based on the analysis method of step 2003 and step 3002, which is recorded as Produce now ,

[0145] Produce now =F(Fault now ∩M2)+F(Faultout now ∩M3),

[0146] Wherein F() represents the third judgment function;

[0147] like Then F(Fault now ∩M2)=0; if Then F(Fault now ∩M2)=1;

[0148] like Then F(Faultout now ∩M3)=0; if Then F(Faultout now ∩M3)=1;

[0149] Step 4002: Generate an early warning signal based on the analysis result of step 4001.

[0150] If Produce now =0, no warning signal is issued.

[0151] If Produce now =1, a Level II warning signal is issued.

[0152] If Produce now =2, a Level I warning signal is issued;

[0153] Step 4003, based on the analysis results of step 4002, notify the relevant staff to perform maintenance operations. When the system identifies a Level II warning signal, notify the relevant staff to perform maintenance on the corresponding links based on the rationality of the products to be mass-produced. When the system identifies a Level I warning signal, notify the relevant staff to perform maintenance on each link of the corresponding products to be mass-produced. When the system does not identify a warning signal, the corresponding products to be mass-produced will be processed for mass production.

[0154] In this embodiment: a device data supervision system based on big data is disclosed (such as Figure 2 As shown), the system is used to implement the specific solution content of the method, and the system includes the following modules:

[0155] Equipment data analysis module: The equipment data analysis module is used to obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation;

[0156] Comprehensive failure risk analysis module: The comprehensive failure risk analysis module is used to analyze the product manufacturing data of the corresponding links of the manufacturing process of the mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored, and to predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links;

[0157] External fault risk analysis module: The external fault risk analysis module is used to analyze the external fault risk situation generated in the assembly and testing link of the corresponding mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored;

[0158] Equipment data rationalization analysis module: The equipment data rationalization analysis module is used to judge the rationality of product mass production based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, and generate early warning signals based on the judgment results.

[0159] The equipment data analysis module includes a data acquisition unit, a deviation analysis unit and a product category classification unit:

[0160] The data acquisition unit is used to obtain the detection report of the corresponding product to be mass-produced in the factory area to be monitored;

[0161] The deviation analysis unit is used to calculate the deviation between the data in the test report of the corresponding product to be mass-produced in the factory area to be monitored and the corresponding theoretical analysis data based on the analysis result of the data acquisition unit;

[0162] The product category classification unit is used to generate an early warning signal based on the analysis result of the deviation analysis unit and the deviation calculation result of the corresponding product to be mass-produced, and classify the products to be mass-produced in the monitored factory area according to the early warning signal.

[0163] The comprehensive fault risk analysis module includes a manufacturing data feasibility analysis unit, a comprehensive fault risk analysis unit and a data recording unit:

[0164] The manufacturing data feasibility analysis unit is used to analyze the manufacturing data feasibility of products in two adjacent links in the manufacturing process of the corresponding product to be mass-produced in the factory area to be monitored;

[0165] The comprehensive failure risk analysis unit is used to calculate the comprehensive failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the manufacturing data feasibility analysis unit;

[0166] The data recording unit is used to record the analysis result of the comprehensive fault analysis unit in real time.

[0167] The external fault risk analysis module includes an assembly test data acquisition unit and an external fault risk analysis unit:

[0168] The assembly test data acquisition unit is used to acquire the data report of the assembly quality inspection link of the corresponding product to be mass-produced;

[0169] The external failure risk analysis unit is used to further analyze the external failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the assembly test data acquisition unit.

[0170] The equipment data rationalization analysis module includes a product rationality analysis unit, a warning condition signal generation unit, and a warning signal elimination unit:

[0171] The product rationality analysis unit is used to calculate the rationality by combining the test results of the manufacturing link and the assembly link of the corresponding product to be mass-produced;

[0172] The early warning condition signal generating unit is used to generate an early warning condition signal according to the analysis result of the product rationality analyzing unit;

[0173] The early warning signal cancellation unit is used to take corresponding measures to cancel the warning in combination with the analysis result of the early warning condition signal generation unit.

[0174] Example 2: Set the test phase of product A to be mass-produced to produce 5 products A to be mass-produced, read the corresponding test values ​​of the products to be mass-produced by the detection device as c1, c2, c3, c4 and c5, and analyze the degree of deviation based on the theoretical analysis value of the monitoring data of product A to be mass-produced, recorded as

[0175]

[0176] According to the deviation degree analysis results, if the deviation degree of the mass-produced product A is not within the standard deviation range, an early warning signal will be issued.

[0177] Randomly select one of the products A to be mass-produced, and analyze the manufacturing data feasibility of the two adjacent links of the product in combination with the manufacturing process of the product A to be mass-produced, which is recorded as Feasibility A , combined with the feasibility of the manufacturing data, further analyze the comprehensive fault risk situation, recorded as Fault A ,

[0178] Based on the data analysis of the assembly test phase of the mass-produced product A, the external fault risk situation is recorded as Faultout A ,

[0179] Faultout A =P(working A )·Vibrate A ,

[0180] Analyze the rationality of the current product to be mass-produced based on the test data of the current product A, denoted as Produce now ,

[0181] If Produce now =0, it indicates that the current products to be mass-produced can be mass-produced and no warning signal is issued.

[0182] If Produce now =1, it indicates that there are problems in the manufacturing process or assembly quality inspection and testing process of the product to be mass-produced, and a Level II warning signal is issued, and relevant staff are notified to carry out maintenance in conjunction with the corresponding links;

[0183] If Produce now =2, it indicates that there are problems in both the manufacturing link and the assembly quality inspection and testing link of the current mass-produced products. A level I warning signal is issued and relevant staff are notified to calibrate the entire production process.

[0184] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0185] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are 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 other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0186] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A device data supervision method based on big data, characterized in that: The method comprises the following steps: S1. Obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation; Step 1001: Obtain a test report of any type of mass-produced product in the factory area to be monitored, and record the test report of the a-th type of mass-produced product as set A. a The test report consists of test data corresponding to one or more test items. in It indicates the test report of the test product numbered n among the products to be mass-produced in the a-th category of the factory area to be monitored, where n indicates the maximum number of the test product among the corresponding products to be mass-produced in the factory area to be monitored; Step 1002: Based on the analysis results in step 1001, theoretical analysis values ​​of the detection data of various types of mass-produced products in the factory area to be monitored are obtained, which are recorded as set B. B=(B1,B2,B3,B a ,...,B m ), Among them B a represents the theoretical analysis report of the detection data of the a-th type of products to be mass-produced in the factory area to be monitored, and m represents the number of types of output to be mass-produced in the factory area to be monitored; Step 1003: Based on the analysis results of step 1001 and step 1002, determine the degree of deviation of the test data of each product to be mass-produced in the factory area to be monitored, and record the degree of deviation of the test data of the test product numbered b in the a-th category of products to be mass-produced in the factory area to be monitored as where b∈[1,n], Where β represents the proportionality coefficient, which is a preset value in the database; α i Indicates the proportionality coefficient of the corresponding data in the test report, and the proportionality coefficient is a preset value in the database; It represents the test data value corresponding to the i-th test item in the test report of the test product numbered b in the a-th type of mass-produced product in the factory area to be monitored; Z i (B a ) represents the theoretical analysis value corresponding to the i-th test item in the theoretical analysis report of the test data of the a-th type of mass-produced products in the factory area to be monitored; j represents the total number of test items in the test report of the corresponding mass-produced products in the factory area to be monitored; Step 1004, looping step 1003 to obtain the degree of deviation of the test data of the corresponding test product in the product to be mass-produced in the factory area to be monitored, and further analyzing the comprehensive deviation degree value of the corresponding product to be mass-produced in combination with the degree of deviation of the test data of the corresponding test product, With point o as the origin, the number of the test product as the x-axis, and the degree of deviation of the test data of the corresponding test product as the y-axis, a first plane rectangular coordinate system is constructed. In the first plane rectangular coordinate system, the coordinate points corresponding to the deviation degree of the test data of the test products corresponding to each serial number of the products to be mass-produced in category a are marked, and two adjacent coordinate points are connected in sequence to generate a fitting curve, which is recorded as N1(x). Based on the theoretical analysis value of the detection data of various types of mass-produced products in the factory area to be monitored, the maximum value of the standard deviation interval of the corresponding products to be mass-produced is obtained; in the first plane rectangular coordinate system, the coordinate point corresponding to the maximum value of the standard deviation interval of the a-th type of products to be mass-produced is marked, and a straight line parallel to the x-axis is constructed through the marked point, recorded as N2(x), then the comprehensive deviation degree value of the a-th type of products to be mass-produced in the factory area to be monitored is ZP a , Wherein γ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database; Step 1005: Based on the analysis result of step 1004, an early warning signal is generated according to the comprehensive deviation degree value of the corresponding product to be mass-produced. If ZP a ≤ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is within the standard deviation range, and no warning signal is issued. If ZP a >ω, it indicates that the comprehensive deviation value of the corresponding product to be mass-produced is not within the standard deviation range, and a warning signal is issued; Step 1006, looping steps 1003 to 1005 to obtain the products to be mass-produced whose comprehensive deviation values ​​of various types of products to be mass-produced in the factory area to be monitored are not within the standard deviation range, and recording the products to be mass-produced in table M1; S2. Based on the working status of the product quality inspection and early warning device in the factory area to be monitored, analyze the product manufacturing data of the corresponding links of the manufacturing process of the products to be mass-produced, and predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links; Step 2001: Based on the analysis results of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the product manufacturing data of the corresponding links of the manufacturing process of the c-th type of products to be mass-produced, which is recorded as set C. c , in represents the product manufacturing data of the corresponding link in the kth manufacturing process of the cth type of mass-produced product in the factory area to be monitored, where k represents the total number of manufacturing processes of the corresponding mass-produced product in the factory area to be monitored; Step 2002: Based on the analysis results of step 2001, the feasibility of manufacturing data of two adjacent links of the manufacturing process of the c-th type of products to be mass-produced is evaluated in turn, which is recorded as Feasibility c , Where τ represents the proportionality coefficient, which is a preset value in the database. It represents the product manufacturing data error status value of the u-th link of the c-th type of mass-produced product in the factory area to be monitored, represents the product manufacturing data error state value of the u+1th link of the cth type of mass-produced product in the factory area to be monitored, and the error state value is read by the detection equipment, H[] represents the conditional judgment function, H1[] represents the first judgment function, like Within the preset range, like Within the preset range, like but like or but Step 2003: Based on the analysis result of step 2002, predict the comprehensive fault risk of the corresponding mass-produced product, and record the comprehensive fault risk of the c-th type of mass-produced product as Fault c , Fault c =-σ·Feasibility c , Wherein σ represents a proportionality coefficient, and the proportionality coefficient is a preset value of the database; Step 2004, looping step 2001 to step 2003 to obtain the comprehensive failure risk situation of each product to be mass-produced in the factory area to be monitored, and recording the failure risk situation in table M2; S3. Analyze the external failure risk generated in the assembly and testing process of the corresponding products to be mass-produced based on the working status of the product quality inspection and early warning devices in the factory area to be monitored; Step 3001: Based on the analysis result of step 1006, randomly obtain a type of products to be mass-produced whose comprehensive deviation degree is not within the standard deviation range in the factory area to be monitored, extract the c-th type of products to be mass-produced in table M1, and obtain the data corresponding to the assembly test link of the c-th type of products to be mass-produced, which is recorded as set D c , in represents the Lth data in the assembly and testing link of the cth type of mass-produced product in the factory area to be monitored, and L represents the total number of data in the assembly and testing link of the corresponding mass-produced product in the factory area to be monitored; Step 3002: Based on the analysis results of step 3001, analyze the external fault risk generated in the assembly and testing phase of the corresponding mass-produced products, and record the external fault risk generated in the assembly and testing phase of the c-th mass-produced products in the monitored factory area as Faultout. c , Faultout c =P(working c )·Vibrate c , Among them working c represents the working status result of the test operation of the c-th type of mass-produced product in the monitored factory, and the working status result is known through the working status indicator light, P() represents the second judgment function, If the working status indicator light is on, then P c )=1, if the working status indicator light is off, then P(working c )=0, Vibrate c Indicates the data value corresponding to the vibration test link of the C-type mass-produced product in the monitored factory, and the data value corresponding to the vibration test link is obtained by monitoring the impact sound between the various parts of the corresponding mass-produced product by the corresponding equipment; Step 3003, looping step 3002 to obtain the external failure risk situation of each assembly and test link of the mass-produced products in the monitored factory area, and recording the failure risk situation in table M3; S4. Based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, judge the rationality of product mass production, and generate early warning signals based on the judgment results; Step 4001: Obtain the test results of the manufacturing and assembly stages of the current product to be mass-produced, and analyze the rationality of the current product to be mass-produced based on the analysis method of step 2003 and step 3002, which is recorded as Produce now , Produce now =F(Fault now ∩M2)+F(Faultout now ∩M3), Wherein F() represents the third judgment function; now represents the type of product to be mass-produced; like Then F(Fault now ∩M2)=0; if Then F(Fault now ∩M2)=1; like Then F(Faultout now ∩M3)=0; if Then F(Faultout now ∩M3)=1; Step 4002: Generate an early warning signal based on the analysis result of step 4001. If Produce now =0, no warning signal is issued. If Produce now =1, a Level II warning signal is issued. If Produce now =2, a Level I warning signal is issued; Step 4003, based on the analysis results of step 4002, notify the relevant staff to perform maintenance operations. When the system identifies a Level II warning signal, notify the relevant staff to perform maintenance on the corresponding links based on the rationality of the products to be mass-produced. When the system identifies a Level I warning signal, notify the relevant staff to perform maintenance on each link of the corresponding products to be mass-produced. When the system does not identify a warning signal, the corresponding products to be mass-produced will be processed for mass production.

2. A device data supervision system based on big data, applied to the device data supervision method based on big data described in claim 1, characterized in that: The system includes the following modules: Equipment data analysis module: The equipment data analysis module is used to obtain the test report of the products to be mass-produced in the factory area to be monitored, analyze the degree of deviation according to the corresponding test data in the test report of the products to be mass-produced, and generate an early warning signal based on the analysis result of the degree of deviation; Comprehensive failure risk analysis module: The comprehensive failure risk analysis module is used to analyze the product manufacturing data of the corresponding links of the manufacturing process of the mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored, and to predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links; External fault risk analysis module: The external fault risk analysis module is used to analyze the external fault risk situation generated in the assembly and testing link of the corresponding mass-produced products based on the working status of the product quality inspection and early warning device in the factory area to be monitored; Equipment data rationalization analysis module: The equipment data rationalization analysis module is used to judge the rationality of product mass production based on the analysis results of the manufacturing and assembly links of the corresponding products to be mass-produced, and generate early warning signals based on the judgment results.

3. The device data monitoring system based on big data according to claim 2 is characterized in that: The equipment data analysis module includes a data acquisition unit, a deviation analysis unit and a product category classification unit: The data acquisition unit is used to obtain the detection report of the corresponding product to be mass-produced in the factory area to be monitored; The deviation analysis unit is used to calculate the deviation between the data in the test report of the corresponding product to be mass-produced in the factory area to be monitored and the corresponding theoretical analysis data based on the analysis result of the data acquisition unit; The product category classification unit is used to generate an early warning signal based on the analysis result of the deviation analysis unit and the deviation calculation result of the corresponding product to be mass-produced, and classify the products to be mass-produced in the monitored factory area according to the early warning signal.

4. The device data monitoring system based on big data according to claim 3 is characterized in that: The comprehensive fault risk analysis module includes a manufacturing data feasibility analysis unit, a comprehensive fault risk analysis unit and a data recording unit: The manufacturing data feasibility analysis unit is used to analyze the manufacturing data feasibility of products in two adjacent links in the manufacturing process of the corresponding product to be mass-produced in the factory area to be monitored; The comprehensive failure risk analysis unit is used to calculate the comprehensive failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the manufacturing data feasibility analysis unit; The data recording unit is used to record the analysis result of the comprehensive fault analysis unit in real time.

5. The device data monitoring system based on big data according to claim 4 is characterized in that: The external fault risk analysis module includes an assembly test data acquisition unit and an external fault risk analysis unit: The assembly test data acquisition unit is used to acquire the data report of the assembly quality inspection link of the corresponding product to be mass-produced; The external failure risk analysis unit is used to further analyze the external failure risk value of the corresponding product to be mass-produced in combination with the analysis result of the assembly test data acquisition unit.

6. The device data monitoring system based on big data according to claim 5 is characterized in that: The equipment data rationalization analysis module includes a product rationality analysis unit, a warning condition signal generation unit, and a warning signal elimination unit: The product rationality analysis unit is used to calculate the rationality by combining the test results of the manufacturing link and the assembly link of the corresponding product to be mass-produced; The early warning condition signal generating unit is used to generate an early warning condition signal according to the analysis result of the product rationality analyzing unit; The early warning signal cancellation unit is used to take corresponding measures to cancel the warning in combination with the analysis result of the early warning condition signal generation unit.

Images