A fault prediction system for headphones based on big data

Abstract

This invention relates to the field of headphone fault prediction technology, addressing the problem that existing headphone testing systems lack the ability to detect and analyze the adaptability of headphones to different application environments. Specifically, it is a headphone fault prediction system based on big data, including a fault prediction platform. This platform is communicatively connected to a hardware analysis module, a hardware rating module, a performance testing module, and a database. The hardware analysis module analyzes and predicts the tensile properties of the test object i and obtains the number of tensile tests. This invention performs applicability testing on headphones that pass the tensile tests, simulating the adaptability of headphones to different application environments. The applicability testing results can be used to match the application scenarios of the headphones and predict the probability of mechanical failures in headphones with different applicability performance under different environments.

Description

Technical Field

[0001] The present invention relates to the technical field of headphone fault prediction, and in particular to a headphone fault prediction system based on big data. Background Art

[0002] Headphones are worn on the head instead of inserted into the ear canal. They are different from in-ear earplugs. They consist of two parts: a signal transmitter and headphones with a signal receiving and amplifying device (usually dynamic). The transmitter is connected to the signal source, and a preamplifier or headphone amplifier can also be connected in front of the transmitter to improve the sound quality and adjust the tone.

[0003] Existing headphones can only be tested for various parameters of the headphones before leaving the factory. However, the probability of mechanical failure of the headphones during use is also related to the application scenario and user usage. Therefore, the headphone parameter test results at the factory cannot reflect the adaptability of the headphones in different application environments, nor can they match the application scenarios of the qualified headphones, and predict and analyze the failures that are likely to occur in the headphones in different application scenarios.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that the existing headphone detection system does not have the function of detecting and analyzing the adaptability of headphones in different application environments and predicting prone faults, and to propose a headphone fault prediction system based on big data.

[0006] The object of the present invention can be achieved by the following technical solutions: A fault prediction system for headphones based on big data, comprising a fault prediction platform, wherein the fault prediction platform is communicatively connected to a hardware analysis module, a hardware rating module, a performance detection module and a database;

[0007] Randomly select n headphones from the same batch of headphones as detection objects i, i, i=1, 2, ..., n, where n is a positive integer;

[0008] The hardware analysis module is used to analyze and predict the stretching performance of the detection object i and obtain the stretching times, sum and average the stretching times LCi of the detection object i to obtain the average times PJ, compare the average times PJ with the times threshold, and determine whether the stretching performance of the detection object is qualified through the comparison result, and perform applicable performance analysis on the headphones with qualified stretching performance;

[0009] The analysis process of the applicability performance includes: establishing a stretching set {JC1, JC2, ..., JCn} based on the stretching times JCi of the detection object i, obtaining the applicability coefficient SY of the detection object by performing variance calculation on the stretching set, obtaining the applicability threshold SYmax through the database, and comparing the applicability coefficient SY of the detection object with the applicability threshold SYmax:

[0010] If the applicability coefficient SY is less than or equal to the applicability threshold SYmax, the applicability performance of the headset is determined to be qualified, and the hardware analysis module sends a qualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received qualified applicability signal to the hardware rating module;

[0011] If the applicability coefficient SY is greater than or equal to the applicability threshold Symax, the applicability performance of the headset is determined to be unqualified, and the hardware analysis module sends an unqualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received unqualified applicability signal to the hardware rating module;

[0012] The hardware rating module is used to assess the hardware grade of the headphones based on tensile performance and applicability performance.

[0013] As a preferred embodiment of the present invention, the tensile performance analysis process includes: selecting n head models and marking them as auxiliary objects, arranging the auxiliary objects from small to large according to the head circumference values, and the difference in head circumference values ​​of adjacent auxiliary objects is 0.5 cm, randomly assigning the n auxiliary objects to the test objects, and conducting wearing tests on the assigned test objects and auxiliary objects.

[0014] As a preferred embodiment of the present invention, the wearing test process includes: wearing the detection object between the two ears of the auxiliary object, then taking off the detection object, measuring the distance between the two earmuffs of the detection object and recording it, increasing the counter value by one, then wearing the detection object between the two ears of the auxiliary object again, then taking off the detection object again, measuring the distance between the two earmuffs of the detection object and recording it, increasing the counter value by one again, and so on; until the distance between the two earmuffs is greater than or equal to the distance threshold, the distance threshold is directly obtained from the database, and the counter value is output.

[0015] As a preferred implementation of the present invention, the comparison process of the average number of times PJ and the number threshold includes:

[0016] If the average number of times PJ is greater than or equal to the number threshold, the stretching performance of the headset is determined to be qualified, and the hardware analysis module sends a stretching qualified signal to the fault prediction platform, and the fault prediction platform sends the received stretching qualified signal to the hardware rating module;

[0017] If the average number of times PJ is less than the number threshold, the stretching performance of the headphones is determined to be unqualified, and the hardware analysis module sends a stretching unqualified signal to the fault prediction platform, and the fault prediction platform sends the received stretching unqualified signal to the hardware rating module.

[0018] As a preferred embodiment of the present invention, the process of hardware grade assessment includes: if the hardware rating module receives an applicable qualified signal, the hardware grade of the headphones is marked as grade one, and the hardware rating module sends a grade one hardware signal to the fault prediction platform; if the hardware rating module receives an applicable unqualified signal, the hardware grade of the headphones is marked as grade two, and the hardware rating module sends a grade two hardware signal to the fault prediction platform; if the hardware rating module receives a stretch unqualified signal, the hardware grade of the headphones is marked as grade three, and the hardware rating module sends a grade three hardware signal to the fault prediction platform.

[0019] As a preferred embodiment of the present invention, the performance detection module is used to detect and analyze the overall performance of the headphones: randomly select a number of headphones as the objects to be tested, and obtain the impedance data ZK, sensitivity data LM and power data GL of the objects to be tested; obtain the performance coefficient XN of the object to be tested by calculating the impedance data ZK, sensitivity data LM and power data GL; obtain the performance thresholds XNmin and XNmax through the database, compare the performance coefficient XN of the object to be tested with the performance thresholds XNmin and XNmax, and judge whether the overall performance of the object to be tested is qualified through the comparison results.

[0020] As a preferred embodiment of the present invention, the process of acquiring the impedance data ZK of the object to be tested includes: using a multimeter to obtain the inductance DG of the object to be tested at a test frequency of 1000 Hz, marking the resistance of the object to be tested as DZ, and obtaining the impedance data ZK of the object to be tested through an impedance calculation formula; the process of acquiring the sensitivity data LM of the object to be tested includes: obtaining the maximum value and the minimum value of the sensitive range through a database, summing and averaging the maximum value and the minimum value of the sensitive range to obtain a sensitive standard value, and marking the absolute value of the difference between the sensitivity of the object to be tested at a test frequency of 1000 Hz and the sensitive standard value as sensitive data LM; the process of acquiring the power data GL of the object to be tested includes: marking the rated power of the object to be tested when in use as power data GL.

[0021] As a preferred embodiment of the present invention, the specific process of comparing the performance coefficient XN of the object to be tested with the performance thresholds XNmin and XNmax includes:

[0022] If XN≤XNmin, the overall performance level of the headset is determined to be level three, and the performance detection module sends a level three performance signal to the fault prediction platform;

[0023] If XNmin<XN<XNmax, the performance detection module sends a secondary performance signal to the fault prediction platform;

[0024] If XN ≥ XNmax, the performance detection module sends a first-level performance signal to the fault prediction platform.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. Through the tensile test, the tensile performance of the headphones is analyzed, so that the headphones with unqualified tensile performance are returned to the factory for processing, to ensure that the tensile performance of the headphones after the test can meet the normal use requirements. For the headphones with qualified tensile performance, the adaptability of the headphones can be analyzed by simulating different application environments. The application scenarios of the headphones can be matched through the applicability performance test results, and the probability of mechanical failure of headphones with different applicability performance in different environments can also be predicted and analyzed;

[0027] 2. The performance detection module can be used to detect and analyze the overall performance of the headphones in combination with the hardware level. The value of the performance coefficient reflects the overall performance of the headphones, and the overall performance of the headphones is rated. The overall quality of the headphones is fed back based on the rating results. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0029] Figure 1 It is a principle block diagram of Embodiment 1 and Embodiment 2 of the present invention;

[0030] Figure 2 This is a method flow chart of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0031] The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 As shown, a fault prediction system for headphones based on big data includes a fault prediction platform, which is communicatively connected to a hardware analysis module, a hardware rating module, a performance detection module and a database.

[0033] Embodiment 1

[0034] First, the tensile performance of the headphones is analyzed through the hardware analysis module, and the mechanical properties of the headphones are determined based on the results of the tensile performance analysis. Headphones with unqualified tensile performance need to be returned to the factory for processing, while headphones with qualified tensile performance need to be determined for their applicability to different types of users. The tensile performance analysis process includes: randomly selecting n headphones from the same batch of headphones as detection objects i, i, i=1, 2, ..., n, n is a positive integer, selecting n head models and marking them as auxiliary objects, arranging the auxiliary objects from small to large according to the head circumference values, and the difference in head circumference values ​​of adjacent auxiliary objects is 0.5 cm, selecting head models with the same number of detection objects and equally increased head circumference values ​​for auxiliary detection, and randomly assigning n auxiliary objects to the detection objects, and performing detection on the assigned objects. The test object and the auxiliary object are subjected to a wearing test, and the process of the wearing test includes: wearing the test object between the two ears of the auxiliary object, then taking off the test object, measuring the distance between the two earmuffs of the test object and recording it, and increasing the counter value by one. This process is to measure the reset function of the test object after stretching, so that the tensile performance of the test object is reflected by the counter value; then wearing the test object between the two ears of the auxiliary object again, and then taking off the test object again, measuring the distance between the two earmuffs of the test object and recording it, and increasing the counter value by one again, and so on; until the distance between the two earmuffs is greater than or equal to the distance threshold, it means that the test object has reached the stretching limit. If it continues to be used, the probability of mechanical failure of the test object is greatly increased. The distance threshold is directly obtained from the database, and the value of the counter is output. The output value of the counter represents the limit stretching times of the corresponding test object.

[0035] The numerical value output by the wearing test is marked as the stretching number LCi, and the stretching number LCi of the test object i is summed and averaged to obtain the average number PJ. The average number represents the overall stretching performance of the same batch of test objects. The average number PJ is compared with the number threshold: if the average number PJ is greater than or equal to the number threshold, the stretching performance of the headphones is determined to be qualified, and the hardware analysis module sends a stretching qualified signal to the fault prediction platform, and the fault prediction platform sends the received stretching qualified signal to the hardware rating module; otherwise, the stretching performance of the headphones is determined to be unqualified, and the hardware analysis module sends a stretching unqualified signal to the fault prediction platform, and the fault prediction platform sends the received unqualified stretching signal to the hardware rating module.

[0036] Secondly, the suitability analysis is performed on the headphones with qualified stretching performance. The purpose of the suitability analysis is to determine the suitability of the headphones with qualified stretching performance when applied to objects with different head circumferences. For application environments where users constantly switch, such as Internet cafes, VR experience halls and other places, the possibility of mechanical failure of headphones with unqualified suitability performance when put into use in the corresponding places is greatly increased. Therefore, the significance of the suitability analysis is to classify and match the application environment of the headphones with qualified stretching performance. The analysis process of the suitability performance includes: establishing a stretching set {JC1, JC2, ..., JCn} based on the stretching times JCi of the detection object i, and using the formula The applicability coefficient SY of the detection object is obtained, and the applicability threshold SYmax is obtained through the database. The applicability coefficient SY of the detection object is compared with the applicability threshold SYmax: if the applicability coefficient SY is less than or equal to the applicability threshold SYmax, the applicability performance of the headphones is determined to be qualified. Headphones with qualified applicability performance can be used in different scenarios and for users with different head circumferences, and their applicability performance is good. The hardware analysis module sends a qualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received qualified applicability signal to the hardware rating module; if the applicability coefficient SY is greater than or equal to the applicability threshold Symax, the applicability performance of the headphones is determined to be unqualified, and the hardware analysis module sends an unqualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received unqualified applicability signal to the hardware rating module.

[0037] The hardware rating module is used to evaluate the hardware level of the headphones through tensile performance and applicability performance. The hardware level evaluation process includes: if the hardware rating module receives an applicable qualified signal, it means that the tensile performance and applicability performance of the headphones are both qualified, and the probability of mechanical failure of this type of headphones when used in different scenarios is small. The hardware level of the headphones is marked as level one, and the hardware rating module sends a level one hardware signal to the fault prediction platform; if the hardware rating module receives an unqualified applicable signal, it means that the tensile performance of the headphones is qualified but the applicability performance is unqualified. The possibility of mechanical failure of this type of headphones under normal application environment is small, but when the user switching frequency is high or the user's head circumference is abnormal, the probability of mechanical failure will increase, and the hardware level of the headphones is marked as level two, and the hardware rating module sends a level two hardware signal to the fault prediction platform; if the hardware rating module receives an unqualified tensile signal, it means that the tensile performance of this type of headphones does not meet the use requirements and needs to be returned to the factory for rework, and the hardware level of the headphones is marked as level three, and the hardware rating module sends a level three hardware signal to the fault prediction platform.

[0038] Embodiment 2

[0039] The overall performance test of the headphones is also particularly important. In this embodiment, the hardware level in the first embodiment is used as a weight influencing factor to test and analyze the overall performance of the headphones. The process of the performance detection module testing and analyzing the overall performance of the headphones is as follows: randomly selecting a number of headphones as the objects to be tested, and obtaining the impedance data ZK, sensitivity data LM and power data GL of the objects to be tested; the impedance data ZK acquisition process of the objects to be tested includes: using a multimeter at a test frequency of 1000 Hz to obtain the inductance DG of the object to be tested, marking the resistance of the object to be tested as DZ, and using the formula Obtain impedance data ZK of the object to be tested; the process of obtaining sensitivity data LM of the object to be tested includes: obtaining the maximum value and the minimum value of the sensitivity range through the database, summing and averaging the maximum value and the minimum value of the sensitivity range to obtain the sensitivity standard value, and marking the absolute value of the difference between the sensitivity of the object to be tested at a test frequency of 1000Hz and the sensitivity standard value as sensitivity data LM; the process of obtaining power data GL of the object to be tested includes: marking the rated power of the object to be tested when in use as power data GL; obtaining the performance coefficient XN of the object to be tested by formula XN=t×(α1×ZK+α2×GL) / (α3×LM), wherein α1, α2, α3 and t are all proportional coefficients, and α3>α2>α1>1; the process of determining the value of t is as follows: : If the hardware level of the object to be inspected is level three, the value of t is 0.85; if the hardware level of the object to be inspected is level two, the value of t is 1; if the hardware level of the object to be inspected is level one, the value of t is 1.15; the performance thresholds XNmin and XNmax are obtained through the database, and the performance coefficient XN of the object to be inspected is compared with the performance thresholds XNmin and XNmax: if XN≤XNmin, the overall performance level of the headset is determined to be level three, and the performance detection module sends a level three performance signal to the fault prediction platform; if XNmin<XN<XNmax, the performance detection module sends a level two performance signal to the fault prediction platform; if XN≥XNmax, the performance detection module sends a level one performance signal to the fault prediction platform.

[0040] Embodiment 3

[0041] See also Figure 2 As shown, a method for predicting headphone faults based on big data includes the following steps:

[0042] Step 1: Detect and analyze the stretching performance of the headphones through the hardware analysis module, select several head models with different head circumferences to match the headphones to be tested, obtain the stretching times of the headphones through a wearing test, obtain the average number of stretching times, and determine whether the stretching performance of the headphones is qualified based on the comparison result of the average number of times and the number threshold;

[0043] Step 2: Perform applicability analysis on headphones with qualified tensile performance, and obtain the applicability coefficient of the headphones through variance calculation. The applicability coefficient is used to reflect the difference in tensile performance when the headphones are used on head models with different head circumferences, so as to determine the applicability of the headphones when applied to different types of users. The smaller the value of the applicability coefficient, the better the tensile performance of the headphones when applied to different types of users, and the larger the scope of application of the headphones;

[0044] Step 3: The hardware rating module evaluates the hardware level of the headphones through stretch performance and applicability and determines the hardware level of the headphones as level one, level two or level three. Headphones with hardware level one have qualified stretch performance and can be applied to users with different head circumferences, and the probability of hardware failure during use is also lower; headphones with hardware level two have qualified stretch performance but can only be applied to users with normal head circumferences. When used by users with head circumferences that are not within the normal range or when users are frequently changed (such as Internet cafes and VR experience halls), the probability of hardware failure is high. Therefore, these headphones can be fully used for factory sales, but are not suitable for use in shared occasions such as Internet cafes and VR experience halls; headphones with hardware level three fail the hardware inspection and cannot be put on sale;

[0045] Step 4: The performance detection module detects and analyzes the overall performance of the headphones and obtains a performance coefficient. The overall performance level of the headphones is determined by comparing the performance coefficient with the performance threshold and the overall performance level of the headphones is determined as level one, level two or level three.

[0046] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula XN=t×(α1×ZK+α2×GL) / (α3×LM); technicians in this field collect multiple groups of sample data and set corresponding performance coefficients for each group of sample data; substitute the set performance coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of α1, α2 and α3 as 1.52, 2.43 and 5.18 respectively;

[0047] The size of the coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding performance coefficient for each set of sample data by technicians in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the performance coefficient is inversely proportional to the value of the sensitive data;

[0048] When the present invention is in use, the stretching performance of the headphones is detected and analyzed through the hardware analysis module, a number of human head models with different head circumferences are selected to match the headphones to be detected, the stretching times of the headphones are obtained through a wearing test, the average times are obtained through the stretching times, and whether the stretching performance of the headphones is qualified is determined based on the comparison result of the average times and the times threshold; the applicability performance analysis is performed on the headphones with qualified stretching performance, and the applicability coefficient of the headphones is obtained through variance calculation, and the applicability coefficient is used to reflect the difference in stretching performance of the headphones when used on human head models with different head circumferences, so as to determine the applicability of the headphones when applied to different types of users.

[0049] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0050] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0051] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A headphone fault prediction system based on big data, comprising a fault prediction platform, characterized in that: The fault prediction platform is communicatively connected with a hardware analysis module, a hardware rating module, a performance detection module and a database; Randomly select n headphones from the same batch of headphones as detection object i, i=1, 2, ..., n, n is a positive integer; The hardware analysis module is used to analyze and predict the stretching performance of the detection object i and obtain the stretching times, sum and average the stretching times LCi of the detection object i to obtain the average times PJ, compare the average times PJ with the times threshold, and judge whether the stretching performance of the detection object is qualified through the comparison result, and perform applicable performance analysis on the headphones with qualified stretching performance, wherein LCi is the stretching set {JC1, JC2, ..., JCm}, and m is the stretching times; The analysis process of the applicability performance includes: obtaining the applicability coefficient SY of the detection object by performing variance calculation on the stretching set, obtaining the applicability threshold SYmax through the database, and comparing the applicability coefficient SY of the detection object with the applicability threshold SYmax: If the applicability coefficient SY is less than or equal to the applicability threshold SYmax, the applicability performance of the headset is determined to be qualified, and the hardware analysis module sends a qualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received qualified applicability signal to the hardware rating module; If the applicability coefficient SY is greater than or equal to the applicability threshold Symax, the applicability performance of the headset is determined to be unqualified, and the hardware analysis module sends an unqualified applicability signal to the fault prediction platform, and the fault prediction platform sends the received unqualified applicability signal to the hardware rating module; The hardware rating module is used to assess the hardware level of the headphones through tensile performance and applicability performance; The tensile performance analysis process includes: selecting n head models and marking them as auxiliary objects, arranging the auxiliary objects in ascending order according to the head circumference values, and the difference in the head circumference values ​​of adjacent auxiliary objects is 0.5 cm, randomly assigning the n auxiliary objects to the test objects, and performing a wearing test on the assigned test objects and auxiliary objects; The process of the wearing test includes: wearing the test object between the two ears of the auxiliary object, then taking off the test object, measuring the distance between the two earmuffs of the test object and recording it, adding one to the counter value, then wearing the test object between the two ears of the auxiliary object again, then taking off the test object again, measuring the distance between the two earmuffs of the test object and recording it, adding one to the counter value, and so on; until the distance between the two earmuffs is greater than or equal to the distance threshold, the distance threshold is directly obtained from the database, the value of the counter is output, and the output value is marked as the stretching number LCi of the test object i; The performance detection module is used to detect and analyze the overall performance of the headphones: randomly select a number of headphones as the objects to be detected, and obtain the impedance data ZK, sensitivity data LM and power data GL of the objects to be detected; obtain the performance coefficient XN of the objects to be detected by calculating the impedance data ZK, sensitivity data LM and power data GL; obtain the performance thresholds XNmin and XNmax through the database, compare the performance coefficient XN of the objects to be detected with the performance thresholds XNmin and XNmax, and determine whether the overall performance of the objects to be detected is qualified based on the comparison results; The process of acquiring the impedance data ZK of the object to be tested includes: using a multimeter to obtain the inductance DG of the object to be tested at a test frequency of 1000 Hz, marking the resistance of the object to be tested as DZ, and obtaining the impedance data ZK of the object to be tested through an impedance calculation formula; the process of acquiring the sensitivity data LM of the object to be tested includes: obtaining the maximum value and the minimum value of the sensitivity range through a database, summing and averaging the maximum value and the minimum value of the sensitivity range to obtain the sensitivity standard value, and marking the absolute value of the difference between the sensitivity of the object to be tested at a test frequency of 1000 Hz and the sensitivity standard value as the sensitivity data LM; the process of acquiring the power data GL of the object to be tested includes: marking the rated power of the object to be tested when in use as the power data GL.

2. The headphone fault prediction system based on big data according to claim 1, characterized in that: The comparison process of the average number of times PJ and the number threshold includes: If the average number of times PJ is greater than or equal to the number threshold, the stretching performance of the headset is determined to be qualified, and the hardware analysis module sends a stretching qualified signal to the fault prediction platform, and the fault prediction platform sends the received stretching qualified signal to the hardware rating module; If the average number of times PJ is less than the number threshold, the stretching performance of the headphones is determined to be unqualified, and the hardware analysis module sends a stretching unqualified signal to the fault prediction platform, and the fault prediction platform sends the received stretching unqualified signal to the hardware rating module.

3. The headphone fault prediction system based on big data according to claim 2, characterized in that: The hardware level assessment process includes: if the hardware rating module receives an applicable qualified signal, the hardware level of the headphones is marked as level one, and the hardware rating module sends a level one hardware signal to the fault prediction platform; if the hardware rating module receives an applicable unqualified signal, the hardware level of the headphones is marked as level two, and the hardware rating module sends a level two hardware signal to the fault prediction platform; if the hardware rating module receives a stretch unqualified signal, the hardware level of the headphones is marked as level three, and the hardware rating module sends a level three hardware signal to the fault prediction platform.

4. The headphone fault prediction system based on big data according to claim 1, characterized in that: The specific process of comparing the performance coefficient XN of the object to be tested with the performance thresholds XNmin and XNmax includes: If XN≤XNmin, the overall performance level of the headset is determined to be level three, and the performance detection module sends a level three performance signal to the fault prediction platform; If XNmin<XN<XNmax, the performance detection module sends a secondary performance signal to the fault prediction platform; If XN ≥ XNmax, the performance detection module sends a first-level performance signal to the fault prediction platform.

Images