Muffler manufacturing process data intelligent analysis method and system

Abstract

The invention is suitable for the technical field of silencer manufacturing, and particularly relates to a silencer manufacturing process data intelligent analysis method and system.The method comprises the steps that installation information of an exhaust system is obtained, the installation information at least comprises user information, the model and the installation time, and sensing equipment deployed in the exhaust system in advance is used for analyzing the installation time of the exhaust system; historical noise elimination data are collected, the corresponding relation between the model and the historical noise elimination data is established, and the historical noise elimination data at least comprise noise and vibration; position data of an exhaust system is obtained and clustered into a plurality of scene categories. By deploying the test equipment, personalized adjustment can be performed on the exhaust system to be delivered to the equipment according to the historical silencing data of the exhaust system, the use matching degree of the silencer and the exhaust system is further enhanced, the use experience of a user is improved, the personalized requirements of the user can be met, and the use experience of the user is improved. Differentiated selling points can be provided for the silencer, and the brand value is improved.

Description

Technical Field

[0001] This invention relates to the field of muffler manufacturing technology, and in particular to a method and system for intelligent analysis of data in the muffler manufacturing process. Background Technology

[0002] The muffler is a key component installed in the exhaust system. Its main function is to reduce the noise generated during equipment operation through its internal multi-layered cavity, baffles, and sound-absorbing materials.

[0003] In the current manufacturing process of mufflers, a standardized and integrated approach is generally adopted. That is, exhaust systems of the same batch are usually equipped with mufflers of the same specifications and structure. However, the usage scenarios of exhaust systems are often relatively simple. If the manufacturing process of mufflers can be adjusted according to this single scenario, for example, by making targeted optimizations in material selection, structural design and the arrangement of internal acoustic cavities, the user experience can be greatly improved.

[0004] Therefore, "how to adjust the muffler manufacturing process according to the high-frequency scenario of the exhaust system" is the technical problem that this invention needs to solve. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for intelligent analysis of muffler manufacturing process data, in order to solve the problem mentioned in the background art of "how to adjust the muffler manufacturing process according to the high-frequency scenario of the exhaust system".

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for intelligent analysis of data from the muffler manufacturing process, the method comprising:

[0008] Acquire installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time; use sensing devices pre-deployed in the exhaust system to collect historical noise reduction data and establish a correspondence between the model and the historical noise reduction data, wherein the historical noise reduction data includes at least: noise and vibration.

[0009] The location data of the exhaust system is acquired and clustered into several scene categories. The test period is selected, the high-frequency category is defined, the preset reference table is queried to obtain the adjustment rules, and the rules are sent to the preset terminals.

[0010] The historical noise reduction data is hashed to obtain a verification value. A mapping between the verification value and the historical noise reduction data is established to construct a preliminary verification mechanism based on similarity.

[0011] By using preset timestamps, a correspondence between location data and historical noise reduction data is established. A test dataset corresponding to each scene category is constructed and sent to a pre-selected test device. Based on the model, the muffler to be delivered is identified and defined as the processing object. The attribute data of the processing object is collected, the evaluation results of the processing object in the test device are obtained, the historical noise reduction data and the test results are compared to obtain the differences, and the attribute data is adjusted.

[0012] Furthermore, the step of collecting historical noise reduction data using sensors pre-deployed in the target device includes:

[0013] Using the aforementioned sensing device, usage data of the exhaust system is collected, a behavioral characteristic pattern is configured, and the distinguishing items are offset.

[0014] Furthermore, the step of collecting historical noise reduction data and establishing the correspondence between model and historical noise reduction data includes:

[0015] The historical noise reduction data is segmented to obtain normal segments and abnormal segments;

[0016] Based on the location data, risk factors for abnormal segments are identified. The location data, abnormal segments, and risk factors are integrated to generate a risk report, which is then sent to a preset terminal.

[0017] Furthermore, the steps of acquiring the location data of the exhaust system, clustering it into several scene categories, selecting a test period, defining a high-frequency category, querying a preset lookup table to obtain adjustment rules, and then sending them to a preset terminal include:

[0018] Using the location data, a movement path map is generated, terrain changes are determined, and the movement path map is divided into several segments;

[0019] Iterate through the scene categories corresponding to each segment, count the number of segments corresponding to each scene category, and define the high-frequency categories.

[0020] Furthermore, the steps of hashing the historical anechoic data to obtain a verification value, establishing a mapping between the verification value and the historical anechoic data, and constructing a preliminary verification mechanism based on similarity include:

[0021] Select a hash function to hash the historical silenced data, define the hash result as the verification value, integrate all the verification values, and generate an index library.

[0022] Real-time noise reduction data is acquired and hashed to obtain target data. The index is queried to determine the verification value with the highest similarity to the target data. The attribute data is then sent to the source terminal of the real-time noise reduction data via the distinguishing item.

[0023] Furthermore, the step of comparing the historical noise reduction data and test results to obtain the differences and adjusting the attribute data includes:

[0024] Record the process of adjusting attribute data and collect usage data after delivery;

[0025] The usage data and historical noise reduction data are integrated to generate a reference feature set, and the adjustment rules and adjustment process are written into the reference feature set.

[0026] Furthermore, the system includes:

[0027] A module is established to acquire installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time. Using sensors pre-deployed in the exhaust system, historical noise reduction data is collected, and a correspondence between the model and the historical noise reduction data is established, wherein the historical noise reduction data includes at least: noise and vibration.

[0028] The distribution module is used to acquire the location data of the exhaust system, cluster it into several scenario categories, select the test period, define the high-frequency category, query the preset reference table, obtain the adjustment rules, and distribute them to the preset terminal.

[0029] A construction module is used to hash the historical noise reduction data to obtain a verification value, establish a mapping between the verification value and the historical noise reduction data, and construct a preliminary verification mechanism based on similarity.

[0030] The adjustment module is used to establish a correspondence between location data and historical noise reduction data via a preset timestamp, construct a test dataset that corresponds one-to-one with each scene category, and send it to a pre-selected test device. Based on the model, it finds the muffler to be delivered and defines it as the processing object, collects the attribute data of the processing object, obtains the evaluation results of the processing object in the test device, compares the historical noise reduction data and the test results, obtains the differences, and adjusts the attribute data.

[0031] Furthermore, the establishment module includes:

[0032] The offset unit is used to collect usage data of the exhaust system using the sensing device, configure a behavior feature pattern, and offset the distinguishing item.

[0033] The unit is used to segment the historical noise reduction data to obtain normal segments and abnormal segments;

[0034] The sending unit is used to determine the risk factors of the abnormal segment through the location data, integrate the location data, the abnormal segment and the risk factors, generate a risk report and send it to a preset terminal.

[0035] Furthermore, the distribution module includes:

[0036] The segmentation unit is used to generate a movement path map using the location data, determine the terrain changes, and segment the movement path map into several segments.

[0037] Define a unit to iterate through the scene categories corresponding to each segment, count the number of segments corresponding to each scene category, and define high-frequency categories.

[0038] Furthermore, the building module includes:

[0039] The generation unit is used to select a hash function, hash the historical silencing data, define the hash result as a verification value, integrate all the verification values, and generate an index library.

[0040] The hash unit is used to acquire real-time noise reduction data, hash it to obtain target data, query the index library to determine the verification value with the highest similarity to the target data, and send the attribute data to the source terminal of the real-time noise reduction data via the distinguishing item.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] By collecting historical muffler data, targeted optimization can be implemented during the manufacturing process, enabling personalized tuning and improving the compatibility between the muffler and the exhaust system. This makes the muffler more aligned with user behavior patterns and daily usage scenarios. By defining adjustment rules, it is possible to more effectively adapt to different operating conditions, further enhancing the muffler's fit with actual usage scenarios. By establishing a preliminary verification mechanism, initial adjustments can be made to the muffler based on users' common scenarios and behavior patterns. By deploying testing equipment, the exhaust system of the equipment to be delivered can be personalized and tuned based on historical muffler data, further enhancing the matching degree between the muffler and the exhaust system, improving the user experience, and not only meeting users' personalized needs but also providing a differentiated selling point for the muffler, thus enhancing brand value. Attached Figure Description

[0043] Figure 1 A flowchart illustrating the intelligent data analysis method for the muffler manufacturing process provided in this embodiment of the invention;

[0044] Figure 2 This is a first sub-flowchart of the intelligent data analysis method for the muffler manufacturing process provided in an embodiment of the present invention;

[0045] Figure 3 This is a second sub-flow diagram of the intelligent data analysis method for the muffler manufacturing process provided in an embodiment of the present invention;

[0046] Figure 4 The third sub-flowchart of the intelligent data analysis method for the muffler manufacturing process provided in the embodiment of the present invention;

[0047] Figure 5 This is a fourth sub-flow diagram of the intelligent data analysis method for the muffler manufacturing process provided in an embodiment of the present invention;

[0048] Figure 6 A block diagram of the intelligent data analysis system for the muffler manufacturing process provided in this embodiment of the invention;

[0049] Figure 7 A block diagram showing the composition of the module in the intelligent data analysis system for the muffler manufacturing process provided in this embodiment of the invention;

[0050] Figure 8 A block diagram of the distribution module in the intelligent data analysis system for the muffler manufacturing process provided in this embodiment of the invention;

[0051] Figure 9 A block diagram of the components of the construction module in the intelligent data analysis system for the muffler manufacturing process provided in this embodiment of the invention;

[0052] Figure 10 This is a block diagram of the adjustment module in the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0054] In Example 1, Figure 1 The implementation flow of the intelligent data analysis method for the muffler manufacturing process provided in this embodiment of the invention is illustrated below, and is described in detail below:

[0055] S100: Obtain installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time; use sensors pre-deployed in the exhaust system to collect historical noise reduction data and establish a correspondence between the model and the historical noise reduction data, wherein the historical noise reduction data includes at least: noise and vibration.

[0056] The installation information of the exhaust system is obtained from the manufacturer or user. This installation information refers to the specific location of the exhaust system installation, the model of the muffler in the exhaust system, and the installation time. In this application, the exhaust system in industrial equipment is taken as an example. Sensing devices are deployed in the user's existing industrial equipment. These sensing devices include noise sensors, vibration sensors, exhaust pressure and flow sensors, etc. The noise and vibration data of the user's existing exhaust system are collected using the sensing devices, and all collected sensing data are defined as historical muffler data. Through the order management system, a corresponding unique identifier is set for each muffler to be delivered, and the corresponding user is identified. Each user corresponds to one historical muffler data. Therefore, each unique identifier also corresponds to one historical muffler data.

[0057] In real life, users who purchase and install mufflers can be divided into two categories: first, those who are purchasing industrial equipment for the first time and have never installed a muffler on their industrial equipment before; and second, those who already own mufflers and are purchasing new ones or replacing them. For the second type of user, the usage data of their existing industrial equipment can be used to provide an adjustment basis for the production of the mufflers to be delivered. Furthermore, for the first type of user who is purchasing a muffler for the first time, universal muffler production parameters can be set to meet basic usage needs and ensure that the exhaust system has stable noise suppression effect and good vibration control performance in most usage scenarios.

[0058] S200: Acquire the location data of the exhaust system, cluster it into several scene categories, select the test period, define the high-frequency category, query the preset reference table, obtain the adjustment rules, and send them to the preset terminal.

[0059] The system receives location data of the user's existing exhaust system, determines the usage scenario, and divides it into several scenario categories with similar characteristics. These scenario categories mainly reflect different usage environments of the exhaust system and muffler, including continuous operation, intermittent operation, variable operating conditions, and heavy load conditions. A test period is selected, which is the time period between when the user completes the muffler procurement process and before delivery. The scenario category with the highest frequency during the test period is defined as the high-frequency category. A preset lookup table is queried, which refers to the "scenario-muffler adjustment rules" lookup table. The adjustment rules corresponding to the high-frequency categories are traversed and distributed to preset terminals, which can be the management terminals for muffler production.

[0060] For example, if a user's high-frequency category is continuous operation, the corresponding adjustment rule is to increase high-frequency noise suppression materials or optimize the internal anechoic chamber structure to reduce high-frequency noise.

[0061] S300: Hash the historical noise reduction data to obtain a verification value, establish a mapping between the verification value and the historical noise reduction data, and construct a preliminary verification mechanism based on similarity.

[0062] Using a pre-selected hash function, such as MD5 or SHA-1, the historical muffler data arranged according to preset rules is hashed, and the resulting hash value is defined as the verification value. Each historical muffler data corresponds to a verification value, establishing a preliminary verification mechanism. The preliminary verification mechanism refers to quickly matching the adjustment rules of the muffler to be delivered by comparing the similarity between two verification values.

[0063] For example, user A's high-frequency category is continuous operation. We obtain user A's historical silencing data and hash it to get A. Now, for users B and C, after obtaining their corresponding historical silencing data, we hash them to get B and C respectively. Using the cosine similarity calculation formula, we calculate the similarity between A and B, and between A and C respectively. If the similarity between A and B is greater than the threshold, user B is directly classified into the continuous operation category, and the silencer corresponding to user B is processed in the same way as user A.

[0064] S400: Establish the correspondence between location data and historical noise reduction data through preset timestamps, construct a test dataset that corresponds one-to-one with each scene category, and send it to the pre-selected test equipment. Based on the model, find the muffler to be delivered and define it as the processing object. Collect the attribute data of the processing object, obtain the evaluation results of the processing object in the test equipment, compare the historical noise reduction data and the test results, obtain the differences, and adjust the attribute data.

[0065] By aligning location data and historical muffler data using pre-embedded timestamps in exhaust systems or industrial equipment, and summarizing historical muffler data from different scenarios based on location information, a test dataset is obtained. This test dataset is then sent to testing equipment, which refers to equipment on the production line used for testing and quality inspection of mufflers, capable of simulating various operating conditions. In practical data use, the location data in the test dataset enhances the realism of the usage scenario, making it more closely resemble actual user experiences. Historical muffler data can correct the test results; when the test results are better than historical muffler data, it indicates that the processed object has been optimized.

[0066] Define the muffler to be delivered as the processing object, collect the attribute data of the processing object, including: number of chambers, layout and resonance point, etc., determine the evaluation result of the processing object in the test equipment, define the difference between historical muffler data and test results as the difference item, send the difference item to the muffler production management personnel, and adjust the attribute data according to the difference item.

[0067] In Example 2, Figure 2 The implementation flow of the intelligent data analysis method for the muffler manufacturing process provided by an embodiment of the present invention is shown below. The steps of collecting historical muffler data using sensors pre-deployed in the target device are described in detail below:

[0068] S101: Using the aforementioned sensing device, collect usage data of the exhaust system, configure a behavioral characteristic pattern, and offset the distinguishing items.

[0069] In addition to noise sensors, vibration sensors, and exhaust pressure and flow sensors, sensing devices may also include pressure sensors and accelerometers to collect usage data from the exhaust system. This usage data includes operational data from industrial equipment, environmental data, and exhaust data. The system analyzes and processes this data to extract user behavior characteristics and determine each user's behavior pattern. Operating modes include aggressive, stable, and economical modes, among others. Adjustments are made to differentiate these patterns based on the user's behavior. For example, if a user's behavior pattern is stable, the corresponding muffler can use a standard chamber design with increased sound-absorbing material thickness to reduce low- and mid-frequency noise and ensure a better user experience.

[0070] In Example 3, Figure 2 The implementation flow of the intelligent data analysis method for the muffler manufacturing process provided by an embodiment of the present invention is illustrated. The following details the steps of collecting historical muffler data and establishing the correspondence between model and historical muffler data:

[0071] S102: The historical noise reduction data is segmented to obtain normal segments and abnormal segments.

[0072] When the historical noise reduction data exceeds the threshold, the corresponding part is defined as the abnormal segment, and the part of the historical noise reduction data other than the abnormal segment is defined as the normal segment.

[0073] S103: Based on the location data, identify the risk factors of the abnormal segment, integrate the location data, abnormal segment, and risk factors, generate a risk report, and send it to the preset terminal.

[0074] Identify the causes of the abnormal segments, i.e., the risk factors. For example, when abnormal segments appear in the vibration data of historical muffler data, the risk factors might be: loose exhaust system connections or the presence of external vibration sources. Write the exhaust system location data, abnormal segments, and risk factors into a preset template, generate a risk report, and send it to a preset terminal, which is the terminal for management personnel in muffler production.

[0075] In Example 4, Figure 3 This paper illustrates the implementation flow of the intelligent data analysis method for the muffler manufacturing process provided by an embodiment of the present invention. The following details the steps of receiving location data uploaded by users of the receiving device, clustering it into several scene categories, selecting a test period, defining high-frequency categories, querying a preset lookup table to obtain adjustment rules, and sending them to a preset terminal, as follows:

[0076] S201: Using the location data, generate a movement path map, determine the terrain changes, and divide the movement path map into several segments.

[0077] By using the collected location data of the exhaust system, it can be determined whether the industrial equipment and exhaust system have moved. If so, the location change is recorded, a movement path map is generated, and the terrain change is marked. For example, a small-scale location adjustment within the same factory building can be regarded as the same terrain, while a large location shift can be defined as another terrain.

[0078] S202: Traverse the scene categories corresponding to each segment, count the number of segments corresponding to each scene category, and define the high-frequency categories.

[0079] Based on the working conditions of each segment, the corresponding scene category is determined, the number of each scene category in the movement path map is counted, and the scene category with the largest number is defined as the high-frequency category.

[0080] In Example 5, Figure 4 The implementation flow of the intelligent data analysis method for the muffler manufacturing process provided by an embodiment of the present invention is illustrated. The following details the steps of hashing the historical muffler data to obtain verification values, establishing a mapping between the verification values ​​and historical muffler data, and constructing a preliminary verification mechanism based on similarity:

[0081] S301: Select a hash function to hash the historical silenced data, define the hash result as a verification value, integrate all verification values, and generate an index library.

[0082] Using a hash function, historical silenced data is hashed, and the resulting hash value is defined as the verification value. All verification values ​​are integrated to obtain an index. In other words, the index is a collection of verification values.

[0083] S302: Acquire real-time noise reduction data, perform hashing to obtain target data, query the index library, determine the verification value with the highest similarity to the target data, and send the attribute data to the source terminal of the real-time noise reduction data via the distinguishing item.

[0084] As illustrated in S300, when it is necessary to adjust the attributes of the processing object corresponding to A, the historical muffler data corresponding to A is first hashed to obtain A, which is the target data. By querying the index library, the verification value with the highest similarity to the target data is determined, assuming it is B. The special processing method for producing the muffler corresponding to B is traced back, and the muffler corresponding to A is processed in the same way.

[0085] In Example 5, Figure 5 The implementation flow of the intelligent data analysis method for the muffler manufacturing process provided by an embodiment of the present invention is illustrated. The following details the steps of comparing the historical muffler data and test results to obtain the differences and adjusting the attribute data:

[0086] S401: Record the process of adjusting attribute data and collect usage data after delivery.

[0087] When adjusting the processing object corresponding to the user, the adjustment process is recorded. The adjustment process may include adjusting the spraying of anti-corrosion coating or the structure of the muffler chamber, the thickness of the sound-absorbing material, etc. At the same time, the usage data of the exhaust system corresponding to the processing object after delivery is collected.

[0088] S402: Integrate the usage data and historical noise reduction data to generate a reference feature set, and write the adjustment rules and adjustment process into the reference feature set.

[0089] The data used is integrated with historical noise reduction data to obtain a reference feature set. The adjustment rules and process are written into the reference feature set, and the entire adjustment process of the muffler is recorded. This makes it easier to optimize the attribute adjustment by referring to the reference features in the subsequent production of the muffler.

[0090] Figure 6 This diagram illustrates the structural block diagram of the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. The intelligent data analysis system 1 for the muffler manufacturing process includes:

[0091] Module 11 is established to acquire installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time. Using sensors pre-deployed in the exhaust system, historical noise reduction data is collected, and a correspondence between the model and the historical noise reduction data is established, wherein the historical noise reduction data includes at least: noise and vibration.

[0092] The distribution module 12 is used to acquire the location data of the exhaust system, cluster it into several scenario categories, select the test period, define the high-frequency category, query the preset reference table, obtain the adjustment rules, and distribute them to the preset terminal.

[0093] Module 13 is used to hash the historical noise reduction data to obtain a verification value, establish a mapping between the verification value and the historical noise reduction data, and construct a preliminary verification mechanism based on similarity.

[0094] The adjustment module 14 is used to establish a correspondence between location data and historical noise reduction data via a preset timestamp, construct a test dataset that corresponds one-to-one with each scene category, and send it to a pre-selected test device. Based on the model, it finds the muffler to be delivered and defines it as the processing object, collects the attribute data of the processing object, obtains the evaluation results of the processing object in the test device, compares the historical noise reduction data and the test results, obtains the differences, and adjusts the attribute data.

[0095] Figure 7 This diagram illustrates the structural block diagram of the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. The establishment module 11 includes:

[0096] The offset unit 111 is used to collect usage data of the exhaust system using the sensing device, configure a behavior feature pattern, and offset the distinguishing item.

[0097] Unit 112 is used to segment the historical noise reduction data to obtain normal segments and abnormal segments;

[0098] The sending unit 113 is used to determine the risk factors of the abnormal segment through the location data, integrate the location data, the abnormal segment and the risk factors, generate a risk report and send it to a preset terminal.

[0099] Figure 8 This diagram illustrates the structural block diagram of the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. The data distribution module 12 includes:

[0100] The segmentation unit 121 is used to generate a movement path map using the location data, determine the terrain changes, and segment the movement path map into several segments.

[0101] Define unit 122 to traverse the scene category corresponding to each segment, count the number of segments corresponding to each scene category, and define the high-frequency category.

[0102] Figure 9 This diagram illustrates the structural block diagram of the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. The building module 13 includes:

[0103] The generation unit 131 is used to select a hash function, hash the historical silenced data, define the hash result as a verification value, integrate all the verification values, and generate an index library.

[0104] The hash unit 132 is used to acquire real-time noise reduction data, hash it to obtain target data, query the index library, determine the verification value with the highest similarity to the target data, and send the attribute data to the source terminal of the real-time noise reduction data via the distinguishing item.

[0105] Figure 10 This diagram illustrates the structural composition of the intelligent data analysis system for the muffler manufacturing process provided in an embodiment of the present invention. The adjustment module 14 includes:

[0106] Recording unit 141 is used to record the adjustment process of attribute data and collect usage data after delivery.

[0107] The writing unit 142 is used to integrate the usage data and historical noise reduction data, generate a reference feature set, and write the adjustment rules and adjustment process into the reference feature set.

[0108] The module 11 is mainly used to complete step S100, the module 12 is mainly used to complete step S200, the module 13 is mainly used to complete step S300, and the module 14 is mainly used to complete step S400.

[0109] The offset unit 111 is mainly used to complete step S101, the obtaining unit 112 is mainly used to complete step S102, and the sending unit 113 is mainly used to complete step S103.

[0110] The segmentation unit 121 is mainly used to complete step S201, and the definition unit 122 is mainly used to complete step S202;

[0111] The generation unit 131 is mainly used to complete step S301, and the hash unit 132 is mainly used to complete step S302.

[0112] The recording unit 141 is mainly used to complete step S401, and the writing unit 142 is mainly used to complete step S402.

[0113] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent data analysis in the manufacturing process of a muffler, characterized in that, The method includes: Acquire installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time; use sensing devices pre-deployed in the exhaust system to collect historical noise reduction data and establish a correspondence between the model and the historical noise reduction data, wherein the historical noise reduction data includes at least: noise and vibration. The location data of the exhaust system is acquired and clustered into several scene categories. The test period is selected, the high-frequency category is defined, the preset reference table is queried to obtain the adjustment rules, and the rules are sent to the preset terminals. The historical noise reduction data is hashed to obtain a verification value. A mapping between the verification value and the historical noise reduction data is established to construct a preliminary verification mechanism based on similarity. By using preset timestamps, a correspondence between location data and historical noise reduction data is established. A test dataset corresponding to each scene category is constructed and sent to a pre-selected test device. Based on the model, the muffler to be delivered is identified and defined as the processing object. The attribute data of the processing object is collected, the evaluation results of the processing object in the test device are obtained, the historical noise reduction data and the test results are compared to obtain the differences, and the attribute data is adjusted.

2. The intelligent data analysis method for the muffler manufacturing process according to claim 1, characterized in that, The step of collecting historical noise reduction data using sensors pre-deployed in the exhaust system includes: Using the aforementioned sensing device, usage data of the exhaust system is collected, a behavioral characteristic pattern is configured, and the distinguishing items are offset.

3. The intelligent data analysis method for the muffler manufacturing process according to claim 1, characterized in that, The steps of collecting historical noise reduction data and establishing the correspondence between model and historical noise reduction data include: The historical noise reduction data is segmented to obtain normal segments and abnormal segments; Based on the location data, risk factors for abnormal segments are identified. The location data, abnormal segments, and risk factors are integrated to generate a risk report, which is then sent to a preset terminal.

4. The intelligent data analysis method for the muffler manufacturing process according to claim 3, characterized in that, The steps of acquiring the location data of the exhaust system, clustering it into several scene categories, selecting a test period, defining high-frequency categories, querying a preset lookup table to obtain adjustment rules, and sending them to preset terminals include: Using the location data, a movement path map is generated, terrain changes are determined, and the movement path map is divided into several segments; Iterate through the scene categories corresponding to each segment, count the number of segments corresponding to each scene category, and define the high-frequency categories.

5. The intelligent data analysis method for the muffler manufacturing process according to claim 3, characterized in that, The steps of hashing the historical anechoic data to obtain a verification value, establishing a mapping between the verification value and the historical anechoic data, and constructing a preliminary verification mechanism based on similarity include: Select a hash function to hash the historical silenced data, define the hash result as the verification value, integrate all the verification values, and generate an index library. Real-time noise reduction data is acquired and hashed to obtain target data. The index is queried to determine the verification value with the highest similarity to the target data. The attribute data is then sent to the source terminal of the real-time noise reduction data via the distinguishing item.

6. The intelligent data analysis method for the muffler manufacturing process according to claim 1, characterized in that, The step of comparing the historical noise reduction data and test results to obtain the differences and adjusting the attribute data includes: Record the process of adjusting attribute data and collect usage data after delivery; The usage data and historical noise reduction data are integrated to generate a reference feature set, and the adjustment rules and adjustment process are written into the reference feature set.

7. A data intelligent analysis system for the muffler manufacturing process, characterized in that, The system includes: A module is established to acquire installation information of the exhaust system, wherein the installation information includes at least: user information, model and installation time. Using sensors pre-deployed in the exhaust system, historical noise reduction data is collected, and a correspondence between the model and the historical noise reduction data is established, wherein the historical noise reduction data includes at least: noise and vibration. The distribution module is used to acquire the location data of the exhaust system, cluster it into several scenario categories, select the test period, define the high-frequency category, query the preset reference table, obtain the adjustment rules, and distribute them to the preset terminal. A construction module is used to hash the historical noise reduction data to obtain a verification value, establish a mapping between the verification value and the historical noise reduction data, and construct a preliminary verification mechanism based on similarity. The adjustment module is used to establish a correspondence between location data and historical noise reduction data via a preset timestamp, construct a test dataset that corresponds one-to-one with each scene category, and send it to a pre-selected test device. Based on the model, it finds the muffler to be delivered and defines it as the processing object, collects the attribute data of the processing object, obtains the evaluation results of the processing object in the test device, compares the historical noise reduction data and the test results, obtains the differences, and adjusts the attribute data.

8. The intelligent data analysis system for the muffler manufacturing process according to claim 7, characterized in that, The establishment module includes: The offset unit is used to collect usage data of the exhaust system using the sensing device, configure a behavior feature pattern, and offset the distinguishing item. The unit is used to segment the historical noise reduction data to obtain normal segments and abnormal segments; The sending unit is used to determine the risk factors of the abnormal segment through the location data, integrate the location data, the abnormal segment and the risk factors, generate a risk report and send it to a preset terminal.

9. The intelligent data analysis system for the muffler manufacturing process according to claim 8, characterized in that, The distribution module includes: The segmentation unit is used to generate a movement path map using the location data, determine the terrain changes, and segment the movement path map into several segments. Define a unit to iterate through the scene categories corresponding to each segment, count the number of segments corresponding to each scene category, and define high-frequency categories.

10. The intelligent data analysis system for the muffler manufacturing process according to claim 8, characterized in that, The building module includes: The generation unit is used to select a hash function, hash the historical silencing data, define the hash result as a verification value, integrate all the verification values, and generate an index library. The hash unit is used to acquire real-time noise reduction data, hash it to obtain target data, query the index library to determine the verification value with the highest similarity to the target data, and send the attribute data to the source terminal of the real-time noise reduction data via the distinguishing item.

Images