Method and system for detecting quality of ultra-thin high-flexibility cable

Abstract

The invention relates to the technical field of inspection, in particular to a method and a system for detecting the quality of an ultra-thin high-flexibility cable. Obtaining design parameters of the target ultra-thin high-flexibility cable; obtaining a parameter fluctuation time sequence vector of the target ultra-thin high-flexibility cable, and constructing a monitoring fluctuation time sequence vector; the method comprises the following steps of: collecting a qualified sample of an ultra-thin high-flexibility cable by taking a design parameter as a retrieval constraint, performing frequent extreme value extraction to obtain a tensile unit preparation parameter fluctuation time sequence vector threshold, a wire doubling parameter fluctuation time sequence vector threshold and a wire winding parameter fluctuation time sequence vector threshold, and constructing a fluctuation time sequence vector threshold; and when the monitoring fluctuation time sequence vector does not meet the fluctuation time sequence vector threshold value, performing quality detection on the target ultra-thin high-flexibility cable to obtain a quality detection result, and sending the quality detection result to a quality management terminal. According to the invention, the technical problems of unreasonable distribution of inspection resources and low inspection precision and inspection efficiency in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of inspection technology, and in particular to a method and system for inspecting the quality of an extremely fine and flexible cable. Background Art

[0002] Ultra-fine and highly flexible cables are widely used in electronic equipment, medical devices and other fields, and their quality directly affects the performance of terminal products. Traditional cable quality inspection mainly adopts sampling inspection method, which tests conductivity, tensile strength and other indicators by randomly selecting samples. This method is based on the assumption that "if the sample is qualified, the batch is qualified", relies on manual setting of inspection standards, and can only detect finished product indicators, and cannot trace the impact of fluctuations in production process parameters on quality. There are technical problems such as unreasonable allocation of inspection resources, low inspection accuracy and low inspection efficiency. Summary of the invention

[0003] The present invention aims to solve the technical problems in the prior art of unreasonable inspection resource allocation, low inspection accuracy and low inspection efficiency of ultra-fine and high-flexible cables, and provides an ultra-fine and high-flexible cable quality inspection method and system to solve the problems.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a method for detecting the quality of an ultra-fine and highly flexible cable, comprising: obtaining the design parameters of an intermediate tensile unit and the design parameters of an outer winding conductor of a target ultra-fine and highly flexible cable; obtaining the fluctuation timing vector of the tensile unit preparation parameters, the fluctuation timing vector of the wire paralleling parameters and the fluctuation timing vector of the wire winding parameters of the target ultra-fine and highly flexible cable, and constructing a monitoring fluctuation timing vector; setting the intermediate tensile unit design parameters and the outer winding conductor design parameters as retrieval constraints, collecting ultra-fine and highly flexible cable quality qualified samples, performing frequent extreme value extraction, obtaining the fluctuation timing vector threshold of the tensile unit preparation parameters, the fluctuation timing vector threshold of the wire paralleling parameters and the fluctuation timing vector threshold of the wire winding parameters, and constructing a fluctuation timing vector threshold; when the monitoring fluctuation timing vector does not meet the fluctuation timing vector threshold, performing a quality inspection on the target ultra-fine and highly flexible cable, obtaining the quality inspection result, and sending it to a quality management terminal.

[0005] Among them, when the monitoring fluctuation timing vector does not meet the fluctuation timing vector threshold, the target ultra-fine and high-flexible cable is quality inspected, including: when the monitoring fluctuation timing vector does not meet the fluctuation timing vector threshold, constructing a monitoring fluctuation deviation timing matrix; processing the monitoring fluctuation deviation timing matrix through a quality anomaly sorting model to obtain a quality index sorting result; and performing quality inspections on the target ultra-fine and high-flexible cables in sequence according to the quality index sorting result.

[0006] Among them, the quality anomaly ranking model includes a conductivity anomaly degree evaluation channel, a tensile strength anomaly degree evaluation channel, a flexibility anomaly degree evaluation channel, and an index ranking channel. Through the quality anomaly probability ranking model, the monitoring fluctuation deviation degree time series matrix is processed to obtain the quality index ranking result, including: inputting the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree; inputting the monitoring fluctuation deviation degree time series matrix into the tensile strength anomaly degree evaluation channel to output the tensile strength anomaly degree; inputting the monitoring fluctuation deviation degree time series matrix into the flexibility anomaly degree evaluation channel to obtain the flexibility anomaly degree; through the index ranking channel, screening the quality indexes that are not equal to 0 among the conductivity anomaly degree, the tensile strength anomaly degree, and the flexibility anomaly degree, sorting them from large to small according to the anomaly degree, and outputting the quality index ranking result.

[0007] Among them, when the monitoring fluctuation time series vector does not meet the fluctuation time series vector threshold, a monitoring fluctuation deviation degree time series matrix is constructed, including: extracting the first moment monitoring fluctuation vector of the first attribute of the monitoring fluctuation time series vector, and extracting the first moment fluctuation vector threshold of the first attribute of the fluctuation time series vector threshold; extracting the first moment fluctuation vector negative threshold and the first moment fluctuation vector positive threshold from the first moment fluctuation vector threshold, where the negative threshold represents a fluctuation threshold less than 0, and the positive threshold represents a fluctuation threshold greater than 0; when the first moment monitoring fluctuation vector is less than 0, calculating the ratio of the first moment monitoring fluctuation vector to the first moment fluctuation vector threshold, and setting it as the first attribute first moment monitoring fluctuation deviation degree; when the first moment monitoring fluctuation vector is equal to 0, setting the first attribute first moment monitoring fluctuation deviation degree to 0; when the first moment monitoring fluctuation vector is greater than 0, calculating the ratio of the first moment monitoring fluctuation vector to the first moment fluctuation vector positive threshold, and setting it as the first attribute first moment monitoring fluctuation deviation degree; adding the first attribute first moment monitoring fluctuation deviation degree to the first moment monitoring fluctuation deviation degree matrix, and adding the first moment monitoring fluctuation deviation degree matrix to the monitoring fluctuation deviation degree time series matrix.

[0008] Among them, inputting the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree includes: obtaining the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix; performing weighted summation calculation on the monitoring fluctuation deviation degree time series matrix according to the monitoring fluctuation attribute weight time series matrix to obtain the fitting deviation degree; calculating the sum of the fitting deviation degree threshold and a small constant, and setting it as the corrected fitting deviation degree threshold; calculating the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and setting it as the conductivity anomaly degree.

[0009] Among them, obtaining the fitting deviation threshold and monitoring the fluctuation attribute weight time series matrix includes: collecting a sample set of ultra-thin, high-flex cables from the target production line; based on the sample set of ultra-thin, high-flex cables, performing correlation weight analysis on the monitoring fluctuation attribute time series matrix based on conductivity to obtain the monitoring fluctuation attribute weight time series matrix; extracting a sample set of ultra-thin, high-flex cables with abnormal conductivity from the sample set of ultra-thin, high-flex cables; according to the monitoring fluctuation attribute weight time series matrix, performing weighted summation calculation on the monitoring fluctuation historical deviation time series matrix of the sample set of ultra-thin, high-flex cables with abnormal conductivity to obtain an abnormal sample fitting deviation set; performing central value analysis on the abnormal sample fitting deviation set to obtain the fitting deviation threshold.

[0010] Optionally, setting the intermediate tensile unit design parameters and the outer winding wire design parameters as retrieval constraints, collecting qualified samples of ultra-thin, high-flex cables, and performing frequent extreme value extraction to obtain the fluctuation time series vector thresholds of the tensile unit preparation parameters, the wire bunching parameter fluctuation time series vector threshold, and the wire winding parameter fluctuation time series vector threshold, including: obtaining the first preparation process of the tensile unit preparation parameters; extracting the first attribute fluctuation vector set of the qualified samples of ultra-thin, high-flex cables belonging to the first preparation process, where the first attribute fluctuation vector set includes a positive fluctuation vector set and a negative fluctuation vector set; respectively deleting outliers from the positive fluctuation vector set and the negative fluctuation vector set to obtain the first attribute positive concentrated fluctuation vector set and the first attribute negative concentrated fluctuation vector set; extracting the minimum value of the first attribute positive concentrated fluctuation vector set, denoted as the first attribute positive fluctuation vector threshold; extracting the maximum value of the first attribute negative concentrated fluctuation vector set, denoted as the first attribute negative fluctuation vector threshold; according to the first attribute positive fluctuation vector threshold and the first attribute negative fluctuation vector threshold, constructing the first attribute fluctuation vector threshold of the first preparation process and adding it to the fluctuation time series vector threshold of the tensile unit preparation parameters; among them, the construction processes of the wire bunching parameter fluctuation time series vector threshold and the wire winding parameter fluctuation time series vector threshold are the same as that of the fluctuation time series vector threshold of the tensile unit preparation parameters.

[0011] In a second aspect, the present invention provides a quality detection system for ultra-thin, high-flex cables, including: A design parameter acquisition module for obtaining the intermediate tensile unit design parameters and the outer winding wire design parameters of the target ultra-thin, high-flex cable; A monitoring fluctuation time series vector construction module for obtaining the fluctuation time series vectors of the tensile unit preparation parameters, the wire bunching parameter fluctuation time series vector, and the wire winding parameter fluctuation time series vector of the target ultra-thin, high-flex cable, and constructing a monitoring fluctuation time series vector; The fluctuating time-series vector threshold construction module is used to set the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints, collect qualified samples of ultra-thin and highly flexible cables, perform frequent extreme value extraction, obtain the fluctuating time-series vector threshold of the tensile unit preparation parameters, the fluctuating time-series vector threshold of the wire bunching parameters, and the fluctuating time-series vector threshold of the wire winding parameters, and construct the fluctuating time-series vector threshold; The quality inspection execution module is used to perform quality inspection on the target ultra-thin and highly flexible cable when the monitored fluctuating time-series vector does not meet the fluctuating time-series vector threshold, obtain the quality inspection result, and send it to the quality management terminal.

[0012] By implementing the present invention, it is possible to obtain the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire of the target ultra-thin and highly flexible cable, so as to establish a unified detection benchmark and avoid the ambiguity of the detection standard caused by unclear design parameters; By implementing the present invention, it is possible to obtain the fluctuating time-series vector of the tensile unit preparation parameters, the fluctuating time-series vector of the wire bunching parameters, and the fluctuating time-series vector of the wire winding parameters of the target ultra-thin and highly flexible cable, construct the monitored fluctuating time-series vector, so as to capture the dynamic changes of production parameters in real time, form a time-series monitoring vector, and cover the entire production process of the cable; By implementing the present invention, it is possible to set the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints, collect qualified samples of ultra-thin and highly flexible cables, perform frequent extreme value extraction, obtain the fluctuating time-series vector threshold of the tensile unit preparation parameters, the fluctuating time-series vector threshold of the wire bunching parameters, and the fluctuating time-series vector threshold of the wire winding parameters, and construct the fluctuating time-series vector threshold, so as to establish a threshold based on actual qualified sample data and avoid misjudgment caused by subjective setting of standards; By implementing the present invention, it is possible to perform quality inspection on the target ultra-thin and highly flexible cable when the monitored fluctuating time-series vector does not meet the fluctuating time-series vector threshold, obtain the quality inspection result, and send it to the quality management terminal, so as to realize the detection of only the cables with abnormal parameter fluctuations, reduce the full inspection cost, improve the detection efficiency, and at the same time give priority to detecting high-risk indicators through a multi-index sorting model (such as from large to small abnormality degree) to improve the screening accuracy of defective products.

[0013] In summary, by implementing the present invention, it is possible to achieve the technical effects of saving inspection resources, greatly improving the inspection accuracy and inspection efficiency during the inspection process of ultra-thin and highly flexible cables. Description of the Drawings

[0014] Figure 1 It is a schematic flow chart of a quality inspection method for an ultra-thin and highly flexible cable provided by the present invention; Figure 2 It is a schematic structural diagram of a quality inspection system for an ultra-thin and highly flexible cable provided by the present invention.

[0015] In the accompanying drawings, the components represented by each reference numeral are as follows: A design parameter acquisition module 11, a monitoring fluctuation time series vector construction module 12, a fluctuation time series vector threshold construction module 13, and a quality inspection execution module 14. Specific implementation manners

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0017] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0018] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or more advantageous than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0019] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a quality detection method for an extremely fine and highly flexible cable, including: S100 Obtain the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire of the target extremely fine and highly flexible cable; S200 Obtain the tensile unit preparation parameter fluctuation time series vector, the wire bunching parameter fluctuation time series vector, and the wire winding parameter fluctuation time series vector of the target extremely fine and highly flexible cable, and construct a monitoring fluctuation time series vector; In S300, taking the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints, collecting qualified samples of the ultra-thin high-flexible cable, performing frequent extreme value extraction, obtaining the threshold of the fluctuation time series vector of the tensile unit preparation parameters, the threshold of the fluctuation time series vector of the wire bunching parameters, and the threshold of the fluctuation time series vector of the wire winding parameters, and constructing the threshold of the fluctuation time series vector. In S400, when the monitored fluctuation time series vector does not meet the threshold of the fluctuation time series vector, perform quality inspection on the target ultra-thin high-flexible cable, obtain the quality inspection result, and send it to the quality management terminal.

[0020] In the embodiment of the present application, the main structure of the ultra-thin high-flexible cable is an intermediate tensile unit and an outer winding wire. Among them, the intermediate tensile unit is made of a high-strength liquid crystal polymer (LCP) material, which plays a role in support and tensile resistance; while the outer winding wire is made of wires such as copper-silver alloy (Cu-Ag), copper-magnesium alloy (Cu-Mg), or copper-tin alloy (phosphor bronze, Cu-Sn-P), and has high conductivity and excellent ductility.

[0021] The production of the ultra-thin high-flexible cable includes three main steps, which are tensile unit production, wire bunching, and conductor winding processing in sequence.

[0022] Among them, the production of the tensile unit is to use a liquid crystal polymer (LCP) material and perform extrusion molding through a high-precision high-temperature extruder. The key parameters are the extrusion temperature (such as 350°C to 380°C) and the extrusion pressure.

[0023] Among them, wire bunching is to use a copper alloy wire with excellent ductility (such as a diameter of 0.010 mm to 0.025 mm) and perform bunching through a micro-tension active wire feeding system and a servo take-up machine. The key parameters are the wire bunching wire feeding tension (such as ≤3 N) and the take-up speed (such as ≤1000 revolutions per minute).

[0024] Among them, conductor winding processing is to wind the tensile unit and the wire through a multi-head high-speed winding machine. The key parameters are the tensile unit wire feeding tension (such as ≤5 N) and the winding speed (such as ≤700 revolutions per minute).

[0025] In step S100 of the embodiment of the present application, obtaining the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire of the target ultra-thin high-flexible cable is to use the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints to perform the collection of qualified samples of the ultra-thin high-flexible cable described in step S300, perform frequent extreme value extraction, obtain the threshold of the fluctuation time series vector of the tensile unit preparation parameters, the threshold of the fluctuation time series vector of the wire bunching parameters, and the threshold of the fluctuation time series vector of the wire winding parameters, and construct the threshold of the fluctuation time series vector.

[0026] Among them, the design parameters of the intermediate tensile unit include the type of polymer material and the first diameter parameter. The type of polymer material is the material used for the intermediate tensile unit, such as polyimide (PI), polyurethane (PU), etc. The first diameter parameter is the designed diameter of the intermediate tensile unit, such as 0.2 mm, 0.15 mm, etc.

[0027] Exemplarily, the design parameters of a certain intermediate tensile unit can be in the form of (PI, 0.2 mm).

[0028] The design parameters of the outer layer winding wire include the wire material type and the second diameter parameter. The wire material type is the wire material of the outer layer winding wire, including various copper alloys such as copper-silver alloy, copper-magnesium alloy, copper-tin alloy, etc. The second diameter parameter is the designed diameter of the outer layer winding wire, such as 0.010 mm, 0.025 mm, etc.

[0029] Exemplarily, the design parameters of a certain outer layer winding wire can be in the form of (silver-plated copper alloy, 0.010 mm).

[0030] The above-mentioned design parameters of the intermediate tensile unit and the outer layer winding wire can be directly obtained from the process design data of the target ultra-thin and highly flexible cable.

[0031] In step S200 of the embodiment of the present application, obtain the tensile unit preparation parameter fluctuation time series vector, wire parallel-stranding parameter fluctuation time series vector, and wire winding parameter fluctuation time series vector of the target ultra-thin and highly flexible cable, and construct a monitoring fluctuation time series vector. Among them, the tensile unit preparation parameters include the extrusion temperature (°C) and the extrusion pressure (MPa). The extrusion temperature is the temperature parameter when the polymer material (such as PI, PU) is extruded and formed during the production of the tensile unit, which directly affects the molecular crystallinity and physical properties of the material. The extrusion pressure is the pressure applied by the extruder to the polymer material to ensure the material density and forming accuracy.

[0032] Among them, the wire parallel-stranding parameters include the wire parallel-stranding pay-off tension (cN, centinewton) and the take-up speed (r / min). The wire parallel-stranding pay-off tension is the tension applied by the micro-tension active pay-off device to a single wire to control the flattening and arrangement accuracy of the wire. The take-up speed is the speed at which the servo take-up machine winds the parallel-stranded wire, which affects the tightness and uniformity of the wire arrangement.

[0033] Among them, the wire winding parameters include the tensile unit pay-off tension (cN, centinewton) and the winding speed (r / min). The tensile unit pay-off tension is the tension when the tensile unit is led out from the pay-off rack during the conductor winding process, which is used to maintain the straightness of the intermediate core. The winding speed is the speed at which the multi-head high-speed winding machine drives the outer layer wire to wind around the tensile unit, which determines the winding pitch and tightness.

[0034] The preparation parameters of the tensile unit, the wire bunching parameters, and the wire winding parameters of the above-mentioned ultra-thin, high-flexibility cable can all be directly obtained from various sensors installed on the ultra-thin, high-flexibility cable production equipment through a PLC (Programmable Logic Controller), and the sampling frequency is 10 Hz (10 times per second). By collecting the preparation parameters of the timing unit, the timing wire bunching parameters, and the timing wire winding parameters of the continuously produced ultra-thin, high-flexibility cable, a time series parameter sequence of the unit preparation parameters, wire bunching parameters, and wire winding parameters can be obtained.

[0035] Furthermore, it is necessary to obtain the time series vector of fluctuations in the preparation parameters of the tensile unit, the time series vector of fluctuations in the wire bunching parameters, and the time series vector of fluctuations in the wire winding parameters of the ultra-thin, high-flexibility cable.

[0036] The construction method of the time series vector of fluctuations in the preparation parameters of the tensile unit, the time series vector of fluctuations in the wire bunching parameters, and the time series vector of fluctuations in the wire winding parameters can be as follows: First, define a reference value, and then subtract the reference value from the real-time parameter to obtain the fluctuation value. That is, the fluctuation value = real-time parameter - reference value. Among them, the reference value can be directly obtained according to the design process document of the ultra-thin, high-flexibility cable.

[0037] For example, for the preparation parameters of the tensile unit, when the reference value of the extrusion temperature is 230 °C and the reference value of the extrusion pressure is 1.2 MPa, if the extrusion temperature at time T1 is 232 °C and the extrusion pressure is 1.15 MPa, then the extrusion temperature fluctuation value is +2 °C, and the extrusion pressure fluctuation value is -0.05 MPa. Then, the extrusion temperature fluctuation value and the extrusion pressure fluctuation value at time t1 can form a time series vector of fluctuations in the preparation parameters of the tensile unit, that is, [temperature fluctuation value, pressure fluctuation value], that is, [+2 °C, -0.05 MPa].

[0038] Then, arrange the fluctuation values at multiple times in chronological order to form a two-dimensional vector, and the time series vector of fluctuations in the preparation parameters of the tensile unit can be formed, that is, [temperature fluctuation sequence, pressure fluctuation sequence]. For example, if there are only 3 recorded times T2, T3, and T4 in the time series vector of fluctuations in the preparation parameters of the tensile unit, then the temperature fluctuation sequence in this time series vector of fluctuations in the preparation parameters of the tensile unit can be: [0, +2, -2]; the pressure fluctuation sequence can be: [0, -0.05, +0.25].

[0039] Based on the same logic as the construction method of the time series vector of fluctuations in the preparation parameters of the tensile unit of the above-mentioned ultra-thin, high-flexibility cable, the time series vector of fluctuations in the wire bunching parameters and the time series vector of fluctuations in the wire winding parameters of the ultra-thin, high-flexibility cable can be constructed, which will not be elaborated here.

[0040] Finally, the three types of parameter fluctuation time series vectors are concatenated in sequence into a three-dimensional matrix to obtain the monitored fluctuation time series vector. That is, the monitored fluctuation time series vector = [tensile unit parameter fluctuation vector, wire parallel and stranded parameter fluctuation vector, wire winding parameter fluctuation vector]. Assuming that data at N time points is collected, the matrix dimension of the monitored fluctuation time series vector is: 3 (parameter types) × 2 (each type contains 2 parameters) × N (time points).

[0041] In step S300 of the embodiment of the present application, taking the intermediate tensile unit design parameters and the outer layer winding wire design parameters as retrieval constraints, collecting qualified samples of ultra-thin and highly flexible cables, performing frequent extreme value extraction, obtaining the thresholds of the tensile unit preparation parameter fluctuation time series vector, the wire parallel and stranded parameter fluctuation time series vector, and the wire winding parameter fluctuation time series vector, and constructing the threshold of the fluctuation time series vector, including: Obtain the first preparation process of the tensile unit preparation parameters; Extract the first attribute fluctuation vector set of the qualified ultra-thin and highly flexible cable samples belonging to the first preparation process, where the first attribute fluctuation vector set includes a positive fluctuation vector set and a negative fluctuation vector set; Delete the outlier points from the positive fluctuation vector set and the negative fluctuation vector set respectively to obtain the first attribute positive concentrated fluctuation vector set and the first attribute negative concentrated fluctuation vector set; Extract the minimum value of the first attribute positive concentrated fluctuation vector set, and set it as the first attribute positive fluctuation vector threshold; Extract the maximum value of the first attribute negative concentrated fluctuation vector set, and set it as the first attribute negative fluctuation vector threshold; According to the first attribute positive fluctuation vector threshold and the first attribute negative fluctuation vector threshold, construct the first preparation process first attribute fluctuation vector threshold and add it to the tensile unit preparation parameter fluctuation time series vector threshold; Among them, the construction processes of the wire parallel and stranded parameter fluctuation time series vector threshold and the wire winding parameter fluctuation time series vector threshold are the same as that of the tensile unit preparation parameter fluctuation time series vector threshold. (Claim 7) In the embodiment of the present application, the first preparation process of the tensile unit preparation parameters refers to the process in the tensile unit preparation process, such as extrusion molding. Among them, in the first preparation process of the tensile unit preparation parameters, there are corresponding several tensile unit preparation parameters, including extrusion temperature (°C), extrusion pressure (MPa). And the tensile unit preparation parameters correspond to the parameter fluctuation time series vectors of several preparation parameters.

[0042] In the embodiments of the present application, it is necessary to obtain the first preparation process of the tensile unit preparation parameters and collect the qualified samples of the ultra-thin high-flexible cable. It is necessary to use the intermediate tensile unit design parameters (polymer material type, first diameter parameter) and the outer winding wire design parameters (wire material type, second diameter parameter) as the database query conditions (i.e., retrieval constraints). From the database of the intermediate tensile unit design parameter fluctuation time series vector, extract the intermediate tensile unit design parameter fluctuation time series vector corresponding to the qualified sample of the ultra-thin high-flexible cable, and extract the first attribute fluctuation vector set of the first preparation process contained in the intermediate tensile unit design parameter fluctuation time series vector.

[0043] The database includes the monitoring fluctuation time series vectors during the production process of multiple ultra-thin high-flexible cable models with different intermediate tensile unit design parameters and outer winding wire design parameters recorded during the production of ultra-thin high-flexible cables within a historical time (such as 1 year).

[0044] The above-mentioned qualified sample of the ultra-thin high-flexible cable refers to the first attribute fluctuation vector set (such as the fluctuation vector set of the extrusion temperature) of the intermediate tensile unit design parameters during the production process corresponding to the qualified ultra-thin high-flexible cable during the extrusion molding process of the intermediate tensile unit (i.e., the first preparation process) here.

[0045] Then, extract the first attribute fluctuation vector set, where the first attribute fluctuation vector set includes a positive fluctuation vector set and a negative fluctuation vector set. The positive fluctuation vector set is the fluctuation with a parameter value higher than the reference value (such as extrusion temperature +2°C, extrusion pressure +0.1 MPa); while the negative fluctuation vector set is the fluctuation with a parameter value lower than the reference value (such as extrusion temperature -1°C, extrusion pressure -0.05 MPa). Furthermore, the mean μ and standard deviation σ of the vector set can be calculated using the 3σ principle (standard deviation method), and the values outside the range of [μ - 3σ, μ + 3σ] are determined as outliers. For example, if the mean of the positive fluctuation vector set is +2°C and the standard deviation is 0.5°C, then +20°C (far exceeding μ + 3σ = +3.5°C) is deleted. Use this method to delete outliers from the positive fluctuation vector set and the negative fluctuation vector set respectively to obtain the first attribute positive concentrated fluctuation vector set and the first attribute negative concentrated fluctuation vector set. The first attribute (such as extrusion temperature) positive concentrated fluctuation vector set can be [+2°C, +1.5°C, +3°C], and the first attribute (such as extrusion temperature) negative concentrated fluctuation vector set can be [-1°C, -0.5°C, -3°C].

[0046] Next, extract the minimum value (i.e., the smallest positive fluctuation value) of the positive set of fluctuation vectors as the positive fluctuation vector threshold. If the positive set of fluctuation vectors is [+1.5°C, +2°C, +3°C], then the minimum value is +1.5°C, that is, the positive threshold is +1.5°C. Extract the maximum value (i.e., the largest negative fluctuation value, e.g., -1°C is greater than -3°C) of the negative set of fluctuation vectors as the negative fluctuation vector threshold. For example, if the negative set of fluctuation vectors is [-3°C, -1°C, -0.5°C], then the maximum value is -0.5°C, that is, the negative threshold is -0.5°C. Through the above method, the positive fluctuation vector threshold and the negative fluctuation vector threshold of the first attribute can be calculated and obtained.

[0047] Finally, combine the positive and negative thresholds into an interval to obtain the first preparation process first attribute fluctuation vector threshold. For example, the fluctuation vector threshold of the extrusion temperature can be [-0.5°C, +1.5°C].

[0048] Finally, add the first preparation process first attribute fluctuation vector threshold (such as the extrusion temperature fluctuation threshold) to the tensile unit preparation parameter fluctuation time series vector threshold; through the above method, multiple attribute fluctuation vector thresholds can be calculated and obtained, and finally combined to obtain the tensile unit preparation parameter fluctuation time series vector threshold.

[0049] Among them, the construction process of the wire parallel and filament parameter fluctuation time series vector threshold and the wire winding parameter fluctuation time series vector threshold is the same as that of the tensile unit preparation parameter fluctuation time series vector threshold, which will not be elaborated here.

[0050] Among them, the construction process of the wire parallel and filament parameter fluctuation time series vector threshold and the wire winding parameter fluctuation time series vector threshold is the same as that of the tensile unit preparation parameter fluctuation time series vector threshold. That is, through the same method, the wire parallel and filament parameter fluctuation time series vector threshold and the wire winding parameter fluctuation time series vector threshold can be calculated and obtained.

[0051] In step S400 of the embodiment of the present application, when the monitored fluctuation time series vector does not meet the fluctuation time series vector threshold, quality inspection is performed on the target ultra-fine high-flex cable, including: When the monitored fluctuation time series vector does not meet the fluctuation time series vector threshold, construct a monitored fluctuation deviation degree time series matrix; Process the monitored fluctuation deviation degree time series matrix through a quality anomaly ranking model to obtain a quality index ranking result; Perform quality inspection on the target ultra-fine high-flex cable in sequence according to the quality index ranking result.

[0052] In step S400 of the embodiment of the present application, when the monitored fluctuation time series vector does not meet the fluctuation time series vector threshold, constructing a monitored fluctuation deviation degree time series matrix includes: Extract the first - moment monitoring fluctuation vector of the first attribute of the monitored fluctuation time - series vector, and extract the first - moment fluctuation vector threshold of the first attribute of the fluctuation time - series vector threshold; Extract the first - moment negative fluctuation vector threshold and the first - moment positive fluctuation vector threshold from the first - moment fluctuation vector threshold, where the negative threshold represents a fluctuation threshold less than 0, and the positive threshold represents a fluctuation threshold greater than 0; When the first - moment monitoring fluctuation vector is less than 0, calculate the ratio of the first - moment monitoring fluctuation vector to the first - moment negative fluctuation vector threshold, and set it as the first - attribute first - moment monitoring fluctuation deviation degree; When the first - moment monitoring fluctuation vector is equal to 0, set the first - attribute first - moment monitoring fluctuation deviation degree to 0; When the first - moment monitoring fluctuation vector is greater than 0, calculate the ratio of the first - moment monitoring fluctuation vector to the first - moment positive fluctuation vector threshold, and set it as the first - attribute first - moment monitoring fluctuation deviation degree; Add the first - attribute first - moment monitoring fluctuation deviation degree to the first - moment monitoring fluctuation deviation degree matrix, and add the first - moment monitoring fluctuation deviation degree matrix to the monitored fluctuation deviation degree time - series matrix.

[0053] In the embodiments of the present application, to construct a monitored fluctuation deviation degree time - series matrix, first, it is necessary to extract the first - moment monitoring fluctuation vector of the first attribute of the monitored fluctuation time - series vector, and extract the first - moment fluctuation vector threshold of the first attribute of the fluctuation time - series vector threshold, and calculate the first - moment monitoring fluctuation deviation degree based on this to obtain the first - moment monitoring fluctuation deviation degree matrix.

[0054] First, it is necessary to extract the first - moment monitoring fluctuation vector of the first attribute of the monitored fluctuation time - series vector. For example, in the monitored fluctuation time - series vector, the first - moment fluctuation of the first attribute (such as extrusion temperature) is + 2°C. Then, obtain the threshold range of the extrusion temperature from the fluctuation time - series vector threshold, such as [-0.5°C, + 1.5°C], and split it into a negative threshold of - 0.5°C and a positive threshold of + 1.5°C.

[0055] If the first - moment monitoring fluctuation vector is less than 0, calculate the ratio of the first - moment monitoring fluctuation vector to the first - moment negative fluctuation vector threshold, and set it as the first - attribute first - moment monitoring fluctuation deviation degree. For example, if the first - moment extrusion temperature fluctuation is + 2°C (>0) and the positive threshold is + 1.5°C; then the monitored fluctuation deviation degree of the first attribute at the first moment = + 2°C / +1.5°C≈1.33.

[0056] If the first - moment monitoring fluctuation vector is equal to 0, set the first - attribute first - moment monitoring fluctuation deviation degree to 0.

[0057] If the monitoring fluctuation vector at the first moment is greater than 0, calculate the ratio of the monitoring fluctuation vector at the first moment to the positive threshold of the fluctuation vector at the first moment, and set it as the monitoring fluctuation deviation degree of the first attribute at the first moment. For example, if the extrusion temperature fluctuation at the first moment is -0.8 °C (<0) and the negative threshold is -0.5 °C; then the monitoring fluctuation deviation degree of the first attribute at the first moment is deviation degree = -0.8 °C / -0.5 °C = 1.6.

[0058] Finally, arrange the deviation degrees of each attribute at the first moment in order to form a row of the matrix. For example, if the extrusion temperature deviation degree is 1.33 and the extrusion pressure deviation degree (hypothetical) is 0.5, then the monitoring fluctuation deviation degree matrix of the first attribute at the first moment is [1.33, 0.5]. Through the above method, the monitoring fluctuation deviation degree matrices of multiple attributes at multiple moments can be calculated.

[0059] Stack the monitoring fluctuation deviation degree matrices of the multiple attributes at multiple moments in chronological order to form a three-dimensional matrix, which is the monitoring fluctuation deviation degree time series matrix.

[0060] In step S400 of the embodiment of the present application, the quality anomaly ranking model includes a conductivity anomaly degree evaluation channel, a tensile strength anomaly degree evaluation channel, a flexibility anomaly degree evaluation channel, and an index ranking channel. Through the quality anomaly probability ranking model, the monitoring fluctuation deviation degree time series matrix is processed to obtain the quality index ranking result, including: Input the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree; Input the monitoring fluctuation deviation degree time series matrix into the tensile strength anomaly degree evaluation channel to output the tensile strength anomaly degree; Input the monitoring fluctuation deviation degree time series matrix into the flexibility anomaly degree evaluation channel to obtain the flexibility anomaly degree; Through the index ranking channel, screen the quality indexes that are not equal to 0 among the conductivity anomaly degree, the tensile strength anomaly degree, and the flexibility anomaly degree, and sort them from largest to smallest in terms of the anomaly degree, and output the quality index ranking result.

[0061] Among them, inputting the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree includes: Obtain the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix; According to the monitoring fluctuation attribute weight time series matrix, perform weighted summation calculation on the monitoring fluctuation deviation degree time series matrix to obtain the fitting deviation degree; Calculate the sum of the fitting deviation degree threshold and a small constant, and set it as the corrected fitting deviation degree threshold; Calculate the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and set it as the conductivity anomaly degree.

[0062] Among them, obtaining the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix includes: Collect a sample set of ultra-thin and highly flexible cables from the target production line; Based on the sample set of ultra-thin and highly flexible cables, perform a correlation weight analysis on the monitoring fluctuation attribute time series matrix based on conductivity to obtain the monitoring fluctuation attribute weight time series matrix; Extract the sample set of ultra-thin and highly flexible cables with abnormal conductivity from the sample set of ultra-thin and highly flexible cables; According to the monitoring fluctuation attribute weight time series matrix, perform a weighted summation calculation on the monitoring fluctuation historical deviation degree time series matrix of the sample set of ultra-thin and highly flexible cables with abnormal conductivity to obtain a set of fitting deviation degrees of abnormal samples; Perform a central value analysis on the set of fitting deviation degrees of the abnormal conductivity samples to obtain the fitting deviation degree threshold.

[0063] In the embodiment of the present application, to obtain the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix, it is first necessary to collect a sample set of ultra-thin and highly flexible cables from the target production line. Specifically, at least 1000 ultra-thin and highly flexible cable samples (with the same intermediate tensile unit design parameters and outer winding wire design parameters) can be continuously collected from the target production line. Each sample is associated with the time series data of each production parameter and the quality inspection results (conductivity, tensile strength, flexibility, etc.). For each sample, arrange the production parameters in a time series to form the aforementioned monitoring fluctuation attribute time series matrix.

[0064] Then calculate the time-varying correlation coefficient between each monitoring fluctuation attribute and the conductivity index. For example, the correlation coefficient between the extrusion temperature and conductivity at time t1 is 0.75, and the correlation coefficient between the extrusion pressure and conductivity is 0.35; the correlation coefficient between the extrusion temperature and conductivity at time t2 is 0.82, and the correlation coefficient between the extrusion pressure and conductivity is 0.41. Among them, the calculation method of the time-varying correlation coefficient (such as sliding window Pearson correlation, rolling covariance calculation, etc.) belongs to the prior art and will not be elaborated here.

[0065] Next, normalize the time-varying correlation coefficient at each time point to obtain the weight. For example, in the above example, the weight of the extrusion temperature at time t1 = 0.75 / (0.75 + 0.35) ≈ 0.68; the weight of the extrusion pressure at time t1 = 0.35 / (0.75 + 0.35) ≈ 0.32.

[0066] Furthermore, it is necessary to extract an abnormal conductivity ultra-fine high-flexible cable sample set from the ultra-fine high-flexible cable sample set. The abnormal conductivity sample set may be a set of samples whose resistance value (such as 70 mΩ) is greater than the design value (such as 50 mΩ) according to the test results.

[0067] Then, the historical deviation of its production parameters (the ratio of the actual value of the production parameters to the reference value) is calculated to form a matrix, and the monitoring fluctuation historical deviation time series matrix of the abnormal conductivity ultra-fine high-flexible cable sample set is obtained. For example, when the reference value of the extrusion temperature is 230°C, the reference value of the extrusion pressure is 1.2MPa, and the extrusion temperature at time t1 is 232°C, and the extrusion pressure is 1.15MPa, then the extrusion temperature historical deviation at time t1 = 232°C / 230°C≈1.0087, and the extrusion pressure historical deviation = 1.15MPa / 1.2MPa≈0.9583. According to the above method, by calculating the historical deviations of multiple production parameters at multiple times and arranging them in chronological order to form a matrix, the monitoring fluctuation historical deviation time series matrix of the abnormal conductivity ultra-fine high-flexible cable sample set can be obtained.

[0068] Furthermore, it is necessary to perform weighted sum calculation on the monitoring fluctuation historical deviation time series matrix of the conductive abnormal ultra-fine and flexible cable sample set according to the monitoring fluctuation attribute weight time series matrix to obtain the abnormal sample fitting deviation set; the calculation method is abnormal sample fitting deviation = Σ (a certain attribute deviation × corresponding moment attribute weight).

[0069] For example, in the above example, when only the extrusion temperature and extrusion pressure are considered, the abnormal sample fitting deviation can be: abnormal sample fitting deviation = extrusion temperature deviation × extrusion temperature weight + extrusion pressure deviation × extrusion pressure weight = 1.33 × 0.68 + 0.5 × 0.32 ≈ 1.03. In the above way, the calculation is repeated for all time points of all abnormal samples to obtain a set of fitting deviations, such as [0.9, 1.1, 1.2, 1.0, 1.3, ...].

[0070] Finally, it is necessary to perform a centralized value analysis on the conductivity anomaly sample fitting deviation set to obtain a fitting deviation threshold. The centralized value analysis method can be to first sort the set and then take the middle value (such as 1.2), then remove the top 10% and bottom 10% extreme values, calculate the mean of the remaining values (such as 1.18), and finally take the median as the threshold (such as 1.2), which represents the typical fluctuation level of the conductivity anomaly sample.

[0071] In the embodiment of the present application, after completing the above steps, it is also necessary to perform a weighted summation calculation on the monitoring fluctuation deviation degree time series matrix according to the monitoring fluctuation attribute weight time series matrix to obtain a fitting deviation degree; calculate the sum of the fitting deviation degree threshold and a small constant, and set it as the corrected fitting deviation degree threshold; calculate the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and set it as the conductivity abnormality degree.

[0072] Still taking the case of only considering two production parameters, namely extrusion temperature and extrusion pressure, as an example. In the embodiment of the present application, the monitoring fluctuation attribute weight time series matrix records the weights of each time point and each production parameter. For example, at time t1 (extrusion temperature weight 0.6, extrusion pressure weight 0.4), and at time t2 (extrusion temperature weight 0.7, extrusion pressure weight 0.3); while the monitoring fluctuation deviation degree time series matrix records the deviation degrees of each time point and each parameter. For example, at time t1 (extrusion temperature deviation degree 1.33, extrusion pressure deviation degree 0.5), and at time t2 (extrusion temperature deviation degree 0.8, extrusion pressure deviation degree 1.2).

[0073] The logic of performing the weighted summation calculation on the monitoring fluctuation deviation degree time series matrix is that for each time point, sum the products of the deviation degrees of each production parameter and the corresponding weights. For example, the fitting deviation degree at time t1 = 1.33×0.6 + 0.5×0.4 = 1.00; the fitting deviation degree at time t2 = 0.8×0.7 + 1.2×0.3 = 0.80. Arranging the fitting deviation degrees in time order gives the finally obtained fitting deviation degree sequence [1.00, 0.80].

[0074] Furthermore, in order to avoid calculation anomalies caused by the threshold being zero or too small, a small constant is needed to correct the fitting deviation degree threshold. The small constant can be taken as 0.01 - 0.1 (such as 0.05). For example, if the original fitting deviation degree threshold is 1.2, then the corrected fitting deviation degree threshold = 1.2 + 0.05 = 1.25.

[0075] Finally, calculate the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and set it as the conductivity abnormality degree. The calculation method of the conductivity abnormality degree can be: conductivity abnormality degree = fitting deviation degree / corrected fitting deviation degree threshold. For example, if the fitting deviation degree at time t1 = 1.00, then the conductivity abnormality degree = 1.00 / 1.25 = 0.8; if the fitting deviation degree at time t2 = 0.80, then the conductivity abnormality degree = 0.80 / 1.25 = 0.64. The closer the conductivity abnormality degree is to 1, the higher the risk of conductivity abnormality.

[0076] Optionally, to simplify the calculation process, if there are multiple time points (such as t1~t3), the mean method can be used for aggregation, that is, calculate the average value of the fitting deviation degrees of all time points. For example, if the fitting deviation degree sequence is [1.00, 0.80, 0.50], then the mean value of the fitting deviation degree is 0.77, and the abnormality degree = 0.77 / 1.25 = 0.62.

[0077] Input the monitored fluctuation deviation degree time series matrix into the electrical conductivity abnormality degree evaluation channel to output the electrical conductivity abnormality degree; Input the monitored fluctuation deviation degree time series matrix into the tensile strength abnormality degree evaluation channel to output the tensile strength abnormality degree; Input the monitored fluctuation deviation degree time series matrix into the flexibility abnormality degree evaluation channel to obtain the flexibility abnormality degree; Through the index sorting channel, screen out the quality indexes that are not equal to 0 among the electrical conductivity abnormality degree, the tensile strength abnormality degree, and the flexibility abnormality degree, sort them in descending order of the abnormality degree, and output the quality index sorting result.

[0078] After the electrical conductivity abnormality degree evaluation channel is built by the above method, it is also necessary to build the tensile strength abnormality degree evaluation channel and the flexibility abnormality degree evaluation channel using the same method.

[0079] Among them, the building logic and calculation logic of the tensile strength abnormality degree evaluation channel and the flexibility abnormality degree evaluation channel are the same as those of the electrical conductivity abnormality degree evaluation channel. Each abnormality degree evaluation channel includes a weight time series matrix (reflecting the influence weight of each production parameter on this index), a fitting deviation degree threshold (the critical value of the abnormality of this index), and an abnormality degree calculation formula (that is: fitting deviation degree / correction threshold). The acquisition methods of the above-mentioned weight time series matrix, fitting deviation degree threshold, and abnormality degree calculation formula have been described in detail during the building process of the electrical conductivity abnormality degree evaluation channel, and will not be elaborated here.

[0080] Among them, the tensile strength refers to the maximum ability of the cable to resist fracture under axial tensile load, and can be measured by the breaking load (unit: centinewton / cN). And the flexibility is used to evaluate the ability of the cable to resist repeated bending, usually measured by the number of bending times (unit: times).

[0081] After the tensile strength abnormality degree evaluation channel, the flexibility abnormality degree evaluation channel, and the electrical conductivity abnormality degree evaluation channel are built, input the monitored fluctuation deviation degree time series matrix into the electrical conductivity abnormality degree evaluation channel to output the electrical conductivity abnormality degree; input the monitored fluctuation deviation degree time series matrix into the tensile strength abnormality degree evaluation channel to output the tensile strength abnormality degree; input the monitored fluctuation deviation degree time series matrix into the flexibility abnormality degree evaluation channel to obtain the flexibility abnormality degree.

[0082] Finally, the anomaly degrees of each index to be detected (such as conductivity, tensile strength, flexibility, etc.) are sorted through the index sorting channel, and the index with the highest anomaly degree is detected first. The input of the index sorting channel is the anomaly degree of each index to be detected (such as conductivity 0.8, tensile strength 1.2, flexibility 0.0). After removing the index with a value of 0 (flexibility), each index to be detected is sorted in descending order of anomaly degree and output to detect the index with the highest anomaly degree first (such as tensile strength).

[0083] Finally, according to the arrangement order of the indexes to be detected output by the index sorting channel, quality inspection is carried out on the target ultra-thin high-flexibility cable to obtain a quality inspection result (including qualified and unqualified), and it is sent to the quality management terminal to complete the quality inspection.

[0084] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the ultra-thin high-flexibility cable quality inspection method provided in Embodiment 1, the embodiment of the present invention further provides an ultra-thin high-flexibility cable quality inspection system, including: A design parameter acquisition module 11, configured to obtain the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire of the target ultra-thin high-flexibility cable; A monitoring fluctuation time series vector construction module 12, configured to obtain the tensile unit preparation parameter fluctuation time series vector, the wire bunching parameter fluctuation time series vector, and the wire winding parameter fluctuation time series vector of the target ultra-thin high-flexibility cable, and construct a monitoring fluctuation time series vector; A fluctuation time series vector threshold construction module 13, configured to set the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints, collect qualified samples of the ultra-thin high-flexibility cable quality, perform frequent extreme value extraction, and obtain the tensile unit preparation parameter fluctuation time series vector threshold, the wire bunching parameter fluctuation time series vector threshold, and the wire winding parameter fluctuation time series vector threshold, and construct a fluctuation time series vector threshold; A quality inspection execution module 14, configured to perform quality inspection on the target ultra-thin high-flexibility cable when the monitoring fluctuation time series vector does not meet the fluctuation time series vector threshold, obtain a quality inspection result, and send it to the quality management terminal.

[0085] Further, the fluctuation time series vector threshold construction module 13 includes the following execution steps: Obtain the first preparation process of the tensile unit preparation parameters; Extract the first attribute fluctuation vector set of the qualified samples of the ultra-thin high-flexibility cable quality belonging to the first preparation process, where the first attribute fluctuation vector set includes a positive fluctuation vector set and a negative fluctuation vector set; Delete the outliers from the positive fluctuation vector set and the negative fluctuation vector set respectively to obtain a first attribute positive concentrated fluctuation vector set and a first attribute negative concentrated fluctuation vector set; Extract the minimum value of the set of positive fluctuation vectors in the first attribute concentration, and set it as the positive fluctuation vector threshold of the first attribute; Extract the maximum value of the set of negative fluctuation vectors in the first attribute concentration, and set it as the negative fluctuation vector threshold of the first attribute; According to the positive fluctuation vector threshold of the first attribute and the negative fluctuation vector threshold of the first attribute, construct the first attribute fluctuation vector threshold for the first preparation process, and add it to the fluctuation time series vector threshold of the preparation parameters of the tensile unit; Among them, the construction process of the fluctuation time series vector threshold of the wire parallel and filament parameters and the fluctuation time series vector threshold of the wire winding parameters is the same as that of the fluctuation time series vector threshold of the preparation parameters of the tensile unit.

[0086] Furthermore, the quality inspection execution module 14 includes the following execution steps: When the monitored fluctuation time series vector does not satisfy the fluctuation time series vector threshold, construct a monitored fluctuation deviation degree time series matrix; through the quality anomaly sorting model, process the monitored fluctuation deviation degree time series matrix to obtain a quality index sorting result; perform quality inspections on the target ultra-fine and highly flexible cable in sequence according to the quality index sorting result.

[0087] Among them, the quality anomaly sorting model includes a conductivity anomaly degree evaluation channel, a tensile strength anomaly degree evaluation channel, a flexibility anomaly degree evaluation channel, and an index sorting channel. By using the quality anomaly probability sorting model to process the monitored fluctuation deviation degree time series matrix, a quality index sorting result is obtained, including: inputting the monitored fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree; inputting the monitored fluctuation deviation degree time series matrix into the tensile strength anomaly degree evaluation channel to output the tensile strength anomaly degree; inputting the monitored fluctuation deviation degree time series matrix into the flexibility anomaly degree evaluation channel to obtain the flexibility anomaly degree; through the index sorting channel, screen out the quality indexes that are not equal to 0 among the conductivity anomaly degree, the tensile strength anomaly degree, and the flexibility anomaly degree, and sort them from largest to smallest according to the anomaly degree, and output the quality index sorting result.

[0088] Among them, when the monitored fluctuation time series vector does not meet the fluctuation time series vector threshold, constructing a monitored fluctuation deviation degree time series matrix includes: extracting the first moment monitored fluctuation vector of the first attribute of the monitored fluctuation time series vector, and extracting the first moment fluctuation vector threshold of the first attribute of the fluctuation time series vector; extracting the first moment fluctuation vector negative threshold and the first moment fluctuation vector positive threshold from the first moment fluctuation vector threshold, where the negative threshold represents a fluctuation threshold less than 0, and the positive threshold represents a fluctuation threshold greater than 0; when the first moment monitored fluctuation vector is less than 0, calculating the ratio of the first moment monitored fluctuation vector to the first moment fluctuation vector threshold, and setting it as the first attribute first moment monitored fluctuation deviation degree; when the first moment monitored fluctuation vector is equal to 0, setting the first attribute first moment monitored fluctuation deviation degree to 0; when the first moment monitored fluctuation vector is greater than 0, calculating the ratio of the first moment monitored fluctuation vector to the first moment fluctuation vector positive threshold, and setting it as the first attribute first moment monitored fluctuation deviation degree; adding the first attribute first moment monitored fluctuation deviation degree into the first moment monitored fluctuation deviation degree matrix, and adding the first moment monitored fluctuation deviation degree matrix into the monitored fluctuation deviation degree time series matrix.

[0089] Among them, inputting the monitored fluctuation deviation degree time series matrix into the conductivity abnormality degree evaluation channel and outputting the conductivity abnormality degree includes: obtaining a fitting deviation degree threshold and a monitored fluctuation attribute weight time series matrix; performing weighted summation calculation on the monitored fluctuation deviation degree time series matrix according to the monitored fluctuation attribute weight time series matrix to obtain a fitting deviation degree; calculating the sum of the fitting deviation degree threshold and a small constant, and setting it as the corrected fitting deviation degree threshold; calculating the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and setting it as the conductivity abnormality degree.

[0090] Among them, obtaining a fitting deviation degree threshold and a monitored fluctuation attribute weight time series matrix includes: collecting a sample set of ultra-thin, highly flexible cables of the target production line; performing correlation weight analysis on the monitored fluctuation attribute time series matrix based on conductivity according to the sample set of ultra-thin, highly flexible cables to obtain a monitored fluctuation attribute weight time series matrix; extracting a sample set of ultra-thin, highly flexible cables with abnormal conductivity from the sample set of ultra-thin, highly flexible cables; performing weighted summation calculation on the monitored fluctuation historical deviation degree time series matrix of the sample set of ultra-thin, highly flexible cables with abnormal conductivity according to the monitored fluctuation attribute weight time series matrix to obtain a set of abnormal sample fitting deviation degrees; performing central value analysis on the set of abnormal sample fitting deviation degrees to obtain a fitting deviation degree threshold.

[0091] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art should understand that the embodiments of the present invention may provide a method, a system or a computer program product. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0093] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be realized by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be realized. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concepts.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and deformations.

Claims

1. A method for detecting the quality of an extremely thin and highly flexible cable, characterized in that, Including: Obtaining the design parameters of the intermediate tensile unit and the design parameters of the outer winding conductor of the target ultra-thin and highly flexible cable; Obtaining the fluctuation time series vector of the preparation parameters of the tensile unit, the fluctuation time series vector of the wire parallel and stranding parameters, and the fluctuation time series vector of the conductor winding parameters of the target ultra-thin and highly flexible cable, and constructing a monitoring fluctuation time series vector; Taking the design parameters of the intermediate tensile unit and the design parameters of the outer winding conductor as retrieval constraints, collecting qualified samples of the ultra-thin and highly flexible cable, performing frequent extreme value extraction, obtaining the threshold values of the fluctuation time series vector of the preparation parameters of the tensile unit, the threshold values of the fluctuation time series vector of the wire parallel and stranding parameters, and the threshold values of the fluctuation time series vector of the conductor winding parameters, and constructing the threshold values of the fluctuation time series vector; When the monitoring fluctuation time series vector does not meet the threshold values of the fluctuation time series vector, performing quality inspection on the target ultra-thin and highly flexible cable, obtaining a quality inspection result, and sending it to the quality management terminal.

2. The method according to claim 1, characterized in that When the monitoring fluctuation time series vector does not meet the threshold values of the fluctuation time series vector, performing quality inspection on the target ultra-thin and highly flexible cable, including: When the monitoring fluctuation time series vector does not meet the threshold values of the fluctuation time series vector, constructing a monitoring fluctuation deviation degree time series matrix; Processing the monitoring fluctuation deviation degree time series matrix through a quality anomaly ranking model to obtain a quality index ranking result; Performing sequential quality inspection on the target ultra-thin and highly flexible cable according to the quality index ranking result.

3. The method according to claim 2, wherein The quality anomaly ranking model includes a conductivity anomaly degree evaluation channel, a tensile strength anomaly degree evaluation channel, a flexibility anomaly degree evaluation channel, and an index ranking channel. Processing the monitoring fluctuation deviation degree time series matrix through a quality anomaly probability ranking model to obtain a quality index ranking result, including: Inputting the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel to output the conductivity anomaly degree; Inputting the monitoring fluctuation deviation degree time series matrix into the tensile strength anomaly degree evaluation channel to output the tensile strength anomaly degree; Inputting the monitoring fluctuation deviation degree time series matrix into the flexibility anomaly degree evaluation channel to obtain the flexibility anomaly degree; Through the index ranking channel, screening out the quality indexes that are not equal to 0 among the conductivity anomaly degree, the tensile strength anomaly degree, and the flexibility anomaly degree, sorting them in descending order of anomaly degree, and outputting the quality index ranking result.

4. The method according to claim 2, wherein When the monitoring fluctuation time series vector does not meet the threshold values of the fluctuation time series vector, constructing a monitoring fluctuation deviation degree time series matrix, including: Extracting the first moment monitoring fluctuation vector of the first attribute of the monitoring fluctuation time series vector, and extracting the first moment fluctuation vector threshold of the first attribute of the fluctuation time series vector threshold; Extracting the first moment fluctuation vector negative threshold and the first moment fluctuation vector positive threshold from the first moment fluctuation vector threshold, where the negative threshold represents the fluctuation threshold less than 0, and the positive threshold represents the fluctuation threshold greater than 0; When the first moment monitoring fluctuation vector is less than 0, calculating the ratio of the first moment monitoring fluctuation vector to the first moment fluctuation vector threshold, and setting it as the first attribute first moment monitoring fluctuation deviation degree; When the first moment monitoring fluctuation vector is equal to 0, setting the first attribute first moment monitoring fluctuation deviation degree to 0; When the monitoring fluctuation vector at the first moment is greater than 0, calculate the ratio of the monitoring fluctuation vector at the first moment to the positive threshold of the fluctuation vector at the first moment, and set it as the monitoring fluctuation deviation degree of the first attribute at the first moment; Add the monitoring fluctuation deviation degree of the first attribute at the first moment into the monitoring fluctuation deviation degree matrix at the first moment, and add the monitoring fluctuation deviation degree matrix at the first moment into the monitoring fluctuation deviation degree time series matrix.

5. The method according to claim 3, wherein Input the monitoring fluctuation deviation degree time series matrix into the conductivity anomaly degree evaluation channel, and output the conductivity anomaly degree, including: Obtain the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix; According to the monitoring fluctuation attribute weight time series matrix, perform weighted summation calculation on the monitoring fluctuation deviation degree time series matrix to obtain the fitting deviation degree; Calculate the sum of the fitting deviation degree threshold and a small constant, and set it as the corrected fitting deviation degree threshold; Calculate the ratio of the fitting deviation degree to the corrected fitting deviation degree threshold, and set it as the conductivity anomaly degree.

6. The method according to claim 5, wherein Obtain the fitting deviation degree threshold and the monitoring fluctuation attribute weight time series matrix, including: Collect a sample set of ultra-thin high-flex cables of the target production line; Based on the sample set of ultra-thin high-flex cables, perform correlation weight analysis on the monitoring fluctuation attribute time series matrix according to conductivity to obtain the monitoring fluctuation attribute weight time series matrix; Extract the sample set of ultra-thin high-flex cables with conductivity anomalies from the sample set of ultra-thin high-flex cables; According to the monitoring fluctuation attribute weight time series matrix, perform weighted summation calculation on the monitoring fluctuation historical deviation degree time series matrix of the sample set of ultra-thin high-flex cables with conductivity anomalies to obtain a set of fitting deviation degrees of abnormal samples; Perform central value analysis on the set of fitting deviation degrees of abnormal samples to obtain the fitting deviation degree threshold.

7. The method according to claim 1, characterized in that, set Taking the design parameters of the intermediate tensile unit and the design parameters of the outer winding wire as retrieval constraints, collect qualified samples of ultra-thin high-flex cables, and perform frequent extreme value extraction to obtain the threshold of the tensile unit preparation parameter fluctuation time series vector, the threshold of the wire bunching parameter fluctuation time series vector, and the threshold of the wire winding parameter fluctuation time series vector, including: Obtain the first preparation process of the tensile unit preparation parameters; Extract the first attribute fluctuation vector set of the qualified samples of ultra-thin high-flex cables belonging to the first preparation process, where the first attribute fluctuation vector set includes a positive fluctuation vector set and a negative fluctuation vector set; Delete the outlier points from the positive fluctuation vector set and the negative fluctuation vector set respectively to obtain the first attribute positive concentrated fluctuation vector set and the first attribute negative concentrated fluctuation vector set; Extract the minimum value of the first attribute positive concentrated fluctuation vector set, and set it as the first attribute positive fluctuation vector threshold; Extract the maximum value of the first attribute negative concentrated fluctuation vector set, and set it as the first attribute negative fluctuation vector threshold; According to the first attribute positive fluctuation vector threshold and the first attribute negative fluctuation vector threshold, construct the first attribute fluctuation vector threshold of the first preparation process, and add it into the tensile unit preparation parameter fluctuation time series vector threshold; Among them, the construction processes of the wire parallel-stranding parameter fluctuation time-series vector threshold and the wire winding parameter fluctuation time-series vector threshold are the same as those of the tensile unit preparation parameter fluctuation time-series vector threshold.

8. A quality inspection system for extremely thin and highly flexible cables, characterized in that, It includes: A design parameter acquisition module, which is used to obtain the intermediate tensile unit design parameters and the outer layer winding wire design parameters of the target ultra-thin and highly flexible cable; A monitoring fluctuation time-series vector construction module, which is used to obtain the tensile unit preparation parameter fluctuation time-series vector, the wire parallel-stranding parameter fluctuation time-series vector, and the wire winding parameter fluctuation time-series vector of the target ultra-thin and highly flexible cable, and construct a monitoring fluctuation time-series vector; A fluctuation time-series vector threshold construction module, which is used to set the intermediate tensile unit design parameters and the outer layer winding wire design parameters as retrieval constraints, collect qualified quality samples of ultra-thin and highly flexible cables, perform frequent extreme value extraction, obtain the tensile unit preparation parameter fluctuation time-series vector threshold, the wire parallel-stranding parameter fluctuation time-series vector threshold, and the wire winding parameter fluctuation time-series vector threshold, and construct a fluctuation time-series vector threshold; A quality inspection execution module, which is used to perform quality inspection on the target ultra-thin and highly flexible cable when the monitoring fluctuation time-series vector does not meet the fluctuation time-series vector threshold, obtain a quality inspection result, and send it to the quality management terminal.

Images