Wire harness production factory cloud point inspection system

Abstract

The invention relates to a wire harness production factory system, in particular to a wire harness production factory cloud point inspection system, which comprises a data collection module, databases, a data analysis module and an intelligent early warning module, and is characterized in that two-dimensional codes generated on scanning equipment in real time are adopted, and data are classified by the system and enter different databases; meanwhile, all the data can be uploaded to a cloud database to be stored, safety is higher, the storage time is longer, meanwhile, the classified data is analyzed in the corresponding database, the transmission and analysis efficiency of the system is greatly improved, the monitoring time is greatly saved, and the monitoring efficiency is improved. According to abnormal data, through implementation of the cloud point inspection system for the wire harness production factory, the reliability of wire harness production can be improved, faults in production can be reduced, real-time monitoring and data analysis can be realized, a more intelligent decision can be made, an intelligent early warning module can help a monitor and a manager to more quickly observe the abnormality of equipment and adjust the production capacity, and the production efficiency is improved. And the production efficiency and quality are improved.

Description

Technical Field

[0001] The present invention relates to a wire harness production factory system, in particular to a wire harness production factory cloud inspection system. Background Art

[0002] Electric wires used to transmit power and signals are constructed to include: a metal conductor with electrical conductivity; and a resin insulator with insulating properties that covers the conductor. In electric wires constructed in this way, the conductor is sometimes referred to as a core wire, a wire conductor portion, etc., and the insulator is sometimes referred to as a coating, a wire coating portion, etc. The conductor of an electric wire is formed by simply bundling or twisting wires. Alternatively, the conductor is sometimes formed of a single-core material instead of wires. The thickness of the electric wire can be represented by the cross-sectional area of ​​the conductor, for example, and there are various thicknesses from small to large. In addition, the thickness of the electric wire also varies depending on the number of wires mentioned above. On the other hand, regarding the insulator, the resin material is selected in consideration of heat resistance, weather resistance, chemical resistance, wear resistance, flame retardancy, etc. In addition, the thickness is appropriately set to ensure insulation.

[0003] A plurality of electric wires are used to form a wiring harness. Regarding the wiring harness, a car is equipped with various electronic devices to achieve the basic performance of the car, that is, the performance and safety of driving, turning, and stopping, and to achieve the convenience and comfort of the car. These various electronic devices use the power and control signals from the battery to operate, and the wiring harness is responsible for transmitting this power and signals. The wiring harness requires various types of wires (length, thickness, insulation material) depending on the type of equipment, the value of the flowing current, the layout location, etc. The wiring harness is a product that processes wires, terminals, and connectors together. It mainly plays the role of control, transmission, and connection. Connecting the circuit board and the control panel is the most common function.

[0004] Tooling, that is, process equipment, refers to the general term for various tools used in the manufacturing process. The existing detection system is unable to collect, analyze, compare and store the data of tooling inspection on the production line of wire harnesses. Therefore, the purpose of the present invention is to provide a cloud inspection system for wire harness production factories. Summary of the Invention

[0005] The purpose of the present invention is to solve the defects of the cloud inspection system for wire harness production plants proposed in the above background technology by proposing a cloud inspection system for wire harness production plants.

[0006] The technical solution adopted in the present invention is as follows:

[0007] A cloud inspection system for a wire harness production plant is provided, comprising a data collection module: for collecting device data by scanning a QR code on the device;

[0008] Database: includes historical database and real-time database. The real-time database classifies the collected data through classification algorithms and stores the classified data in the historical database.

[0009] Data analysis module: The data analysis module analyzes the data in the real-time database through a comparison algorithm to obtain normal data and abnormal data;

[0010] Intelligent early warning module: used to issue early warnings for abnormal data.

[0011] As a preferred technical solution of the present invention: the data collection module collects information on the equipment's operating time, production volume and product model by scanning the real-time QR code generated on the tooling cutting board equipment.

[0012] As a preferred technical solution of the present invention: the database is used to classify and store the data obtained by scanning the QR code of the tooling cutting board equipment. The normal database divides the data into a first database and a second database through a classification module classification algorithm according to different monitored equipment models.

[0013] As a preferred technical solution of the present invention: the real-time data in the database is compared and classified with the historical data in the historical database, and then stored in the normal database and the abnormal database of the historical database.

[0014] As a preferred technical solution of the present invention: the classification module in the database classifies the obtained data through a classification algorithm, and the classification algorithm formula is as follows:

[0015]

[0016] Where J represents the classification function; m represents the amount of data;

[0017] y (i) The label of a database representing data (i) is 1 for the first type of device corresponding to the first database, and 0 for the second type of device corresponding to the second database;

[0018] λ is the regularization parameter, which is used to control the regularization term in the classification function;

[0019] x (i) is the eigenvector of the data; h θ (x (i) ) represents the algorithm’s predicted output for data (i); d(x (i) ,x ref ) represents a similarity metric function used to measure the feature vector x of data (i) (i) With a certain eigenvector x ref The difference between the d(x(i) ,x ref )’s data similarity algorithm formula is as follows:

[0020]

[0021] in represents the jth feature of data (i); x refj Indicates the reference standard data x ref The jth feature of ; ∑ means summing all features;

[0022] When data is classified according to device type, similarity can be used to measure the similarity between device data, and device data with the same label can be classified into one category based on the similarity value. Device data with greater similarity are classified into the same category.

[0023] As a preferred technical solution of the present invention: the data analysis module is based on a comparison algorithm, which is used to compare the data with the corresponding standard values ​​in the first database and the second database to determine whether the data is abnormal.

[0024] As a preferred technical solution of the present invention: the comparison algorithm formula in the data analysis module is as follows:

[0025] Z–score=(x-μ) / σ;

[0026] The Z-score represents the similarity between the data and the mean value of the data in the original database and is calculated in units of standard deviation;

[0027] x represents the input data;

[0028] μ represents the average value of the data in the first and second databases;

[0029] σ represents the standard deviation of the data in the first database and the second database.

[0030] As a preferred technical solution of the present invention: the intelligent early warning module includes a lighting module and a voice module, and the intelligent early warning module issues an early warning for abnormal results through the lighting module and the voice module.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] In this cloud inspection system for a wire harness production plant, a QR code containing device data information generated in real time on the device is scanned, and the data is classified by the system and entered into different databases. At the same time, all the data will be uploaded to the cloud database for storage, which is safer and has a longer storage time. At the same time, the classified data is analyzed in the corresponding database, which greatly improves the transmission and analysis efficiency of the system and greatly saves monitoring time. Abnormal data can improve the reliability of the production line harness, reduce production failures, realize real-time monitoring and data analysis, and help make more informed decisions through the implementation of the cloud inspection system for wire harness production plants. The intelligent early warning module can help monitors and managers observe equipment abnormalities more quickly and adjust production volume to improve production efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is the overall process flow of the present invention.

[0034] The meaning of each mark in the figure is:

[0035] 1. Data collection module;

[0036] 2. Database;

[0037] 3. Data analysis module;

[0038] 4. Intelligent early warning module. DETAILED DESCRIPTION

[0039] It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this embodiment can be combined with each other. The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 making creative efforts are within the scope of protection of the present invention.

[0040] See also Figure 1 As shown, a cloud inspection system for a wire harness production plant is provided, comprising a data collection module 1: for collecting device data by scanning a QR code on the device;

[0041] Database 2: includes a historical database and a real-time database. The real-time database classifies the collected data using a classification algorithm and stores the classified data in the historical database.

[0042] Data analysis module 3: The data analysis module analyzes the data in the real-time database through a comparison algorithm to obtain normal data and abnormal data;

[0043] Intelligent early warning module 4: used to issue early warnings for abnormal data.

[0044] The data collection module 1 uses a code scanning method, and an intelligent cloud inspection management system is installed in the code scanning device. The cloud inspection management system uses cloud storage to store and analyze the data obtained by the scanning device. The device is equipped with a QR code generation tool that encodes the data into a QR code image to generate a real-time QR code, which can timely transmit the data collection in the device to generate the latest QR code information. Database 2 is used to classify and store the data collected by code scanning, and classify the data into a first database and a second database according to the type of device. Data analysis module 3 is used to analyze and compare the input data and transmit abnormal data to intelligent warning module 4, so that intelligent warning module 4 can issue a warning by turning the module light red and providing a voice prompt.

[0045] Data collection module 1 collects equipment information by scanning the QR code on the tooling cutting board. By scanning the real-time QR code generated by the tooling cutting board and regularly scanning the QR code on the equipment, data collection module 1 can better evaluate the performance of the equipment, allocate processing capacity according to production needs, and maximize the production efficiency of the equipment.

[0046] Database 2 is used to classify and store the data obtained by scanning the QR code of the tooling cutting board equipment. The normal database divides the data into a first database and a second database through the classification algorithm of the classification module according to the different models of the monitored equipment. Database 2 is further divided into two databases according to the different models of the monitored equipment. The database is divided into a normal database and an abnormal database. The normal database is divided into a first database and a second database. The normal database is used to store normal data, and the abnormal database is used to store abnormal data. When the data is input into the database, it will first be temporarily stored in the real-time database. The data in the real-time database is compared by the data analysis module 3 to obtain normal data and abnormal data. Then, the normal data and abnormal data are compared and classified with the historical data through the classification algorithm and input into the corresponding first database and second database. This makes later analysis more convenient and makes the cloud inspection system respond faster, improving computing efficiency.

[0047] The real-time data in Database 2 is compared and classified with the historical data in the historical database, and then stored in the normal database and abnormal database of the historical database. The historical database is divided into a support database and an abnormal database to facilitate subsequent comparison and review. All data in Database 2 will be uploaded to the cloud database for better, longer-term, and more accurate storage and review. The cloud database will update the equipment's working status and abnormality reports in real time for managers to review at any time. Managers can track the completion of tasks through the system and take measures to resolve problems when necessary. All data is stored in a secure cloud database to better ensure data integrity and availability, while implementing appropriate security measures to protect sensitive information from unauthorized access. At the same time, data uploaded to the cloud database can be operated and viewed in other applications, not limited to smart scanning devices, which makes it easier for managers to allocate production capacity.

[0048] The classification module in database 2 classifies the obtained data using a classification algorithm. The classification algorithm formula is as follows:

[0049]

[0050] Where J represents the classification function; m represents the amount of data;

[0051] y (i) The label of a database representing data (i) is 1 for the first type of device corresponding to the first database, and 0 for the second type of device corresponding to the second database;

[0052] λ is the regularization parameter, which is used to control the regularization term in the classification function;

[0053] x (i) is the eigenvector of the data; h θ (x (i) ) represents the algorithm’s predicted output for data (i); d(x (i) ,x ref ) represents a similarity metric function used to measure the feature vector x of data (i) (i) With a certain eigenvector x ref The difference between d(x (i) ,x ref )’s data similarity algorithm formula is as follows:

[0054]

[0055] in represents the jth feature of data (i); x refj Indicates the reference standard data x ref The jth feature of ; ∑ means summing all features;

[0056] When classifying data based on device type, similarity can be used to measure the similarity between device data, and device data with the same label can be classified into one category based on the similarity value. Device data with greater similarity are classified into the same category. After data classification, it is input into the corresponding database, which can quickly compare the data with the standard values ​​in the corresponding database and export the results faster, thereby improving the calculation speed.

[0057] The data analysis module 3 is based on a comparison algorithm, which is used to compare the data with the corresponding standard values ​​in the first database and the second database to determine whether the data is abnormal.

[0058] The comparison algorithm formula in data analysis module 3 is as follows:

[0059] Z–score=(x-μ) / σ;

[0060] The Z-score represents the distance between the data and the average value of the data in the original database, and is calculated in units of standard deviation. The Z-score value of the data is determined by calculating the difference between the data and the average value and dividing it by the standard deviation. When the Z-score value is greater than 3 or less than -3, the data is an outlier and is transmitted to the intelligent warning module 4 for warning.

[0061] X represents the input data;

[0062] μ represents the average value of the data in the first and second databases;

[0063] σ represents the standard deviation of the data in the first database and the second database.

[0064] After all the data in the database 2 are analyzed and compared in the data analysis module 3, the abnormal data obtained will be promptly transmitted to the intelligent early warning module 4. The intelligent early warning module 4 will promptly transmit the warning information to the application interface of the intelligent scanning device, and will also upload the information of the abnormal data to the cloud database, so that the manager can check the abnormal equipment in time and adjust the production status of the equipment.

[0065] Intelligent warning module 4 includes a lighting module and a voice module. These modules are used to issue warnings regarding abnormal results obtained by data analysis module 3. The lighting module of intelligent warning module 4 is located on the system interface of the intelligent scanning device and other viewable applications. When abnormal data from one device is uploaded to the system, the corresponding module on the intelligent scanning device's application interface changes from green to red, alerting the monitor of the device anomaly. Simultaneously, the voice module of the intelligent monitoring device emits a sound, providing better alerts to monitors and enabling more timely review of device status.

[0066] After a device has scanned and collected data, the monitor will regularly scan the QR code generated on the device to collect the device data after working for a period of time, and store the device data in the cloud database. At the same time, the monitor will compare the data with previous periods, allowing managers to better control the operation information of the equipment, set the appropriate production workload for the equipment, and make the equipment more efficient.

[0067] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

[0068] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A cloud inspection system for a wire harness production plant, characterized by: include: Data collection module (1): used to collect device data by scanning the QR code on the device; Database (2): includes a historical database and a real-time database. The real-time database classifies the collected data using a classification algorithm and stores the classified data in the historical database. Data analysis module (3): The data analysis module analyzes the data in the real-time database through a comparison algorithm to obtain normal data and abnormal data; Intelligent early warning module (4): used to issue early warning for abnormal data.

2. The wire harness production factory cloud inspection system according to claim 1 is characterized by: The data collection module (1) collects information on the equipment's operating time, production volume, and product model by scanning the real-time QR code generated on the tooling cutting board equipment.

3. The wire harness production factory cloud inspection system according to claim 1 is characterized by: The database (2) is used to classify and store data obtained by scanning the QR code of the tooling cutting board equipment. The normal database divides the data into a first database and a second database through a classification algorithm of a classification module according to different monitored equipment models.

4. The wire harness production factory cloud inspection system according to claim 1 is characterized by: The real-time data in the database (2) is compared and classified with the historical data in the historical database, and then stored in the normal database and the abnormal database of the historical database.

5. The wire harness production factory cloud inspection system according to claim 3 is characterized by: The classification module in the database (2) classifies the obtained data using a classification algorithm, and the classification algorithm formula is as follows: Where J represents the classification function; m represents the amount of data; y (i) The label of a database representing data (i) is 1 for the first type of device corresponding to the first database, and 0 for the second type of device corresponding to the second database; λ is the regularization parameter, which is used to control the regularization term in the classification function; x (i) is the eigenvector of the data; h θ (x (i) ) represents the algorithm’s predicted output for data (i); d(x (i) ,xref) represents a similarity metric function used to measure the feature vector x of data (i) (i) With a certain eigenvector x ref The difference between the d(x (i) ,x ref )’s data similarity algorithm formula is as follows: in represents the jth feature of data (i); x refj Indicates the reference standard data x ref The jth feature of ∑ means summing all features; When data is classified according to device type, similarity can be used to measure the similarity between device data, and device data with the same label can be classified into one category based on the similarity value. Device data with greater similarity are classified into the same category.

6. The wire harness production factory cloud inspection system according to claim 5 is characterized by: The data analysis module (3) is based on a comparison algorithm, which is used to compare the data with the corresponding standard values ​​in the first database and the second database to determine whether the data is abnormal.

7. The wire harness production factory cloud inspection system according to claim 6, characterized in that: The comparison algorithm formula in the data analysis module (3) is as follows: Z–score=(x-μ) / σ; Z-score is the similarity between the data and the average value of the standard data in the original database; x represents the input data; μ represents the average value of the data in the first and second databases; σ represents the standard deviation of the data in the first database and the second database.

8. The wire harness production factory cloud inspection system according to claim 1 is characterized by: The intelligent early warning module (4) comprises a lighting module and a voice module, and the intelligent early warning module (4) issues an early warning for abnormal results through the lighting module and the voice module.

Images