Anti-interference communication wire harness production safety supervision system based on neural network

Abstract

The invention belongs to the technical field of data processing, and mainly relates to an anti-interference communication wire harness production safety supervision system based on a neural network. The first monitoring terminal is used for performing real-time production state monitoring on production equipment in a production workshop and dividing production state data of the production equipment into a first feature vector containing at least one feature type based on various features of the production equipment; the second monitoring terminal is used for carrying out anti-interference communication monitoring on the wire harness produced by the production equipment in real time and dividing anti-interference communication data of the wire harness into a second feature vector containing at least one feature type; the neural network unit judges the anti-interference communication state of the wire harness produced by the production equipment pointed by the first feature vector through the first feature vector and / or the neural network unit judges the safety state of the production equipment corresponding to the wire harness pointed by the second feature vector through the second feature vector; therefore, the technical defect that an existing wire harness production safety supervision system cannot perform real-time monitoring is overcome.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to an anti-interference communication wire harness production safety supervision system based on a neural network. Background Art

[0002] Wire harnesses are widely used in automobiles, aviation, communications, and industrial equipment, and are indispensable components in electronic systems. With the rapid development of technology, the performance requirements for wire harnesses are also continuously increasing, especially in terms of electromagnetic interference (EMI) resistance, signal integrity, and overall safety. Therefore, a safety supervision system for the wire harness production process is particularly important. Through an effective supervision system, various risks in the production process can be monitored, potential problems can be discovered and solved in a timely manner, thereby avoiding safety hazards caused by unqualified quality.

[0003] Although existing wire harness production safety supervision systems have improved production processes and management procedures based on market feedback and quality inspection results, there are still technical defects. The main reason is that existing systems mainly rely on post-production data analysis and lack dynamic monitoring of the real-time production process, making it impossible to identify abnormal states on the production line in a timely manner. This causes many problems to be discovered only after production is completed, resulting in increased repair costs and delivery delays. At the same time, due to the lack of real-time monitoring, quality problems that occur during the production process often cannot be traced back to specific production equipment or production stages, making it impossible to effectively improve quality and production efficiency.

[0004] Consequently, existing technical solutions have the technical defect that it is impossible to predict the quality of wire harnesses during the production process, especially when the state of production equipment changes, it is difficult to give early warnings about the quality of wire harnesses according to production conditions, thus affecting the overall product quality.

[0005] Based on this, it is urgent to improve the existing anti-interference communication wire harness production safety supervision system to solve the technical defects existing in the prior art. Summary of the Invention

[0006] The object of the present invention is to provide, in view of the deficiencies of the prior art, an anti-interference communication wire harness production safety supervision system that can perform real-time production supervision on wire harnesses and the production equipment for producing wire harnesses based on a neural network.

[0007] To achieve the above technical object, the present application implements the following technical solutions:

[0008] An anti-interference communication wire harness production safety supervision system based on a neural network, comprising a first monitoring terminal, a second monitoring terminal, and a control terminal connected to both the first monitoring terminal and the second monitoring terminal;

[0009] The first monitoring terminal is used to monitor the real-time production status of production equipment in the production workshop and divide the production status data of the production equipment into a first feature vector including at least one feature type based on various features of the production equipment;

[0010] The second monitoring terminal is used to monitor the anti-interference communication of the wire harness produced by the production equipment in real time and divide the anti-interference communication data of the wire harness into a second feature vector including at least one feature type;

[0011] The control end includes a processing module and a neural network unit connected to the processing module; the processing module is communicatively connected to the first monitoring terminal and the second monitoring terminal and transmits the first feature vector and the second feature vector to the neural network unit;

[0012] The neural network unit determines the anti-interference communication state of the wire harness produced by the production equipment pointed to by the first feature vector through the first feature vector and / or the neural network unit determines the safety state of the production equipment corresponding to the wire harness pointed to by the second feature vector through the second feature vector.

[0013] The above technical solution has the following technical effects:

[0014] The technical solution of this application proposes an anti-interference communication wire harness production safety supervision system based on a neural network to solve the limitations of the prior art. Specifically, the system monitors the real-time status of production equipment by setting the first monitoring terminal, and at the same time monitors the anti-interference communication of the produced wire harness by the second monitoring terminal. These two monitoring terminals can generate two feature vectors with the same or different dimensions. The first feature vector represents the state of the production equipment, and the second feature vector represents the anti-interference performance of the wire harness, ensuring comprehensive real-time data collection.

[0015] The system transmits the real-time generated feature vectors (the first feature vector and the second feature vector) to the processing module of the control end for analysis by the neural network unit. The neural network model can perform deep learning based on historical data and real-time collected data, so as to judge the anti-interference communication state of the wire harness and the safety state of the production equipment. When there is a significant difference between the real-time state and the model prediction value, the system can automatically trigger an alarm and key monitoring to provide timely risk warning.

[0016] In summary, the above technical solution solves the defects of the existing wire harness production safety supervision system in terms of real-time performance, traceability and prediction ability by introducing real-time monitoring, feature vector analysis and intelligent decision-making.

[0017] As a further improvement to an anti-interference communication wire harness production safety supervision system based on a neural network of the present invention, the processing module adds a first time stamp Tc to the first feature vector, and the processing module adds a second time stamp Tm to the second feature vector;

[0018] The first timestamp Tc is used to indicate the time when the wire harness is monitored during the production process of the production equipment;

[0019] The second timestamp Tm is used to record the time when the production equipment is monitored during the production process.

[0020] As a further improvement to a production safety supervision system for anti-interference communication wire harnesses based on a neural network according to the present invention, the processing module defines the time window as W. When the first timestamp Tc of the first feature vector processed by the processing module and the second timestamp Tm of the second feature vector satisfy: |Tc - Tm| ≤ W, the first feature vector and the second feature vector are associated.

[0021] As a further improvement to a production safety supervision system for anti-interference communication wire harnesses based on a neural network according to the present invention, the neural network unit includes a training set and an input set. The training set inputs, through an external device, a third feature vector of the production equipment in an abnormal state and / or a fourth feature vector of the wire harness in an abnormal state; wherein, the feature type of the third feature vector is the same as that of the first feature vector, and the feature type of the fourth feature vector is the same as that of the second feature vector;

[0022] The input set is used to input the first feature vector of the production equipment during real-time production and the second feature vector of the wire harness produced by the production equipment in real-time.

[0023] As a further improvement to a production safety supervision system for anti-interference communication wire harnesses based on a neural network according to the present invention, the neural network unit judges the similarity between the first feature vector and the third feature vector, and the similarity between the second feature vector and the fourth feature vector through similarity analysis; the expression of the similarity analysis is:

[0024]

[0025] wherein, S is the similarity value, V c is the first feature vector, V m is the second feature vector.

[0026] As a further improvement to a production safety supervision system for anti-interference communication wire harnesses based on a neural network according to the present invention, the neural network unit conducts similarity analysis on the first feature vector and the third feature vector;

[0027] When the similarity value between the first feature vector and the third feature vector is greater than the first threshold, the neural network unit judges that the production equipment pointed to by the first feature vector is in an abnormal state.

[0028] As a further improvement to a production safety supervision system for anti-interference communication wiring harnesses based on a neural network according to the present invention, the neural network unit performs a similarity analysis on the second feature vector and the fourth feature vector;

[0029] When the similarity value between the second feature vector and the fourth feature vector is greater than the second threshold, the neural network unit determines that the wiring harness pointed to by the second feature vector is in an abnormal state.

[0030] As a further improvement to a production safety supervision system for anti-interference communication wiring harnesses based on a neural network according to the present invention, the feature type of the first feature vector is at least one of signal-to-noise ratio, electromagnetic interference level, response time, and power loss.

[0031] As a further improvement to a production safety supervision system for anti-interference communication wiring harnesses based on a neural network according to the present invention, the feature type of the second feature vector is at least one of device temperature, output power, and working time.

[0032] As a further improvement to a production safety supervision system for anti-interference communication wiring harnesses based on a neural network according to the present invention, the system further includes a host computer communicatively connected to the processing module. The processing module outputs the anti-interference communication state of the wiring harness produced by the production equipment pointed to by the first feature vector determined by the neural network unit and / or the safety state of the production equipment corresponding to the wiring harness pointed to by the second feature vector determined by the neural network unit to the host computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention and form a part of the present invention. The illustrative embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0034] Figure 1 is a schematic structural diagram of Embodiment 1 of the present invention;

[0035] Figure 2 is a schematic structural diagram of the control end in Embodiment 1 of the present invention;

[0036] Figure 3 is a schematic structural diagram of the neural network unit in Embodiment 1 of the present invention;

[0037] Wherein:

[0038] 1 - First monitoring terminal;

[0039] 11 - Production equipment;

[0040] 2 - Second monitoring terminal;

[0041] 21 - Wiring harness;

[0042] 3 - Control terminal;

[0043] 31 - Processing module;

[0044] 32 - Neural network unit;

[0045] 321 - Training set;

[0046] 322 - Output set;

[0047] 4 - Host computer. Specific implementation manner

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used in the specification of the present application herein are only for the purpose of describing specific embodiments, and are not intended to limit the present application.

[0049] In the description of the present invention, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected", and "fixed" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Although the present application is disclosed above with preferred embodiments, it is not used to limit the claims. Any person skilled in the art can make several possible changes and modifications without departing from the concept of the present application. Therefore, the protection scope of the present application should be defined by the scope of the claims of the present application.

[0051] Next, in combination with the specific implementation manner, the present invention will be further described in detail, but the embodiments of the present invention are not limited thereto.

[0052] Embodiment 1

[0053] As Figures 1 - 3As shown in the figure, in order to solve the problem that the existing production safety supervision system of the anti-interference communication wire harness 21 cannot provide real-time feedback on the safety status of the production equipment 11 in the production workshop and the evaluation of the quality of the anti-interference communication wire harness 21. This application has improved the existing production safety supervision system of the anti-interference communication wire harness 21. Specifically, the production safety supervision system of the anti-interference communication wire harness 21 in this application is improved based on a neural network. Among them, the production safety supervision system of the anti-interference communication wire harness 21 includes a first monitoring terminal 1, a second monitoring terminal 2, and a control terminal 3 connected to both the first monitoring terminal 1 and the second monitoring terminal 2; the first monitoring terminal 1 is used to monitor the real-time production status of the production equipment 11 in the production workshop and divide the production status data of the production equipment 11 into a first feature vector containing at least 1 feature type based on various characteristics of the production equipment 11; the second monitoring terminal 2 is used to monitor the anti-interference communication of the wire harness 21 produced by the production equipment 11 in real time and divide the anti-interference communication data of the wire harness 21 into a second feature vector containing at least 1 feature type; the control terminal 3 includes a processing module 31 and a neural network unit 32 connected to the processing module 31; the processing module 31 is communicatively connected to the first monitoring terminal 1 and the second monitoring terminal 2 and transmits the first feature vector and the second feature vector to the neural network unit 32; the neural network unit 32 determines the anti-interference communication status of the wire harness 21 produced by the production equipment 11 pointed to by the first feature vector through the first feature vector and / or the neural network unit 32 determines the safety status of the production equipment 11 corresponding to the wire harness 21 pointed to by the second feature vector through the second feature vector.

[0054] Further, the working principle of the above technical solution is that after the processing module 31 transmits the collected first feature vector and second feature vector to the neural network unit 32, the neural network unit 32 uses the trained model to analyze these feature vectors. The model analysis process embedded in the neural network unit 32 includes feature extraction, feature matching, and status judgment. In the feature extraction stage, the neural network unit 32 will extract the key information related to the status of the production equipment 11 in the first feature vector, such as signal-to-noise ratio, electromagnetic interference level, response time, and power loss, etc. At the same time, it will also extract the key information related to the anti-interference performance of the wire harness 21 in the second feature vector, such as equipment temperature, output power, working time, etc. These key information serve as the basis for subsequent analysis.

[0055] In the feature matching stage, the neural network unit 32 will perform similarity analysis on the real-time collected feature vector and the abnormal state feature vector stored in the training set 321. By calculating the similarity between the real-time feature vector and the abnormal feature vector, the neural network unit 32 can determine whether there is a possibility of an abnormal state for the current production equipment 11 or wire harness 21. If the similarity exceeds the preset threshold, it indicates that there may be an abnormal state.

[0056] In the state judgment stage, the neural network unit 32 comprehensively judges the safety state of the production equipment 11 and the anti-interference communication state of the wire harness 21 according to the result of feature matching. If the judgment result is an abnormal state, the processing module 31 will immediately trigger an alarm and send the abnormal information to the host computer so that the operator can take timely measures for intervention. At the same time, the system will automatically record the information of the abnormal state, including the time of the abnormality occurrence, the type of the abnormality, and the relevant feature vectors, providing data support for subsequent quality analysis and production improvement. For example, when the neural network unit 32 judges through the first feature vector that the state of the production equipment 11 pointed to by the first feature vector is abnormal, it can be inferred that the anti-interference communication state of the produced wire harness 21 is also abnormal. At this time, the processing module 31 performs alarm processing and drives the first monitoring terminal 1 to monitor the wire harness 21 produced by the production equipment 11 pointed to by the first feature vector again. It should be noted that in the actual process of detecting the wire harness 21, due to the excessive number of wire harnesses 21 and the error rate of the detection equipment, some wire harnesses 21 may not be detected because the abnormal amount of anti-interference communication performance is small, and the above problems are avoided by the technical solution of the present application. At the same time, the neural network unit 32 judges the safety state of the production equipment 11 corresponding to the wire harness 21 pointed to by the second feature vector through the second feature vector, and similarly reduces the monitoring error of the production equipment 11.

[0057] Further, the feature type of the first feature vector is at least one of signal-to-noise ratio, electromagnetic interference level, response time, and power loss; the feature type of the second feature vector is at least one of equipment temperature, output power, and working time. In the specific implementation process, the state of the production equipment 11 is represented by the following feature vector Vm:

[0058]

[0059] Among them, Temperature is the equipment temperature (°C), PowerOutput is the output power (W), and WorkingHours is the working time (hours). Assume that the current state of the production equipment 11 is: Temperature = 65 °C; PowerOutput = 140 W; WorkingHours = 10. Then the feature vector corresponding to the production equipment 111 is:

[0060]

[0061] Further, the monitoring device represents the anti-interference performance of the wire harness 21 through the feature vector Vc:

[0062]

[0063] Among them, SNR is the signal-to-noise ratio (dB), EMI is the electromagnetic interference level (dB), ResponseTime is the response time (ms), and PowerLoss is the power loss (W). Assume that the anti-interference communication monitoring data of the wire harness 21 produced by the current production equipment 11 are: SNR = 28 dB, EMI = 2.5 dB, ResponseTime = 4 ms, PowerLoss = 0.08 W. Then the feature vector of the wire harness 21 is expressed as:

[0064]

[0065] In summary, a production safety supervision system for anti-interference communication wire harness 21 based on neural network according to the present invention realizes the comprehensive supervision of the production process of the wire harness 21 by real-time monitoring the state of the production equipment 11 and the anti-interference performance of the wire harness 21, and using the neural network model for analysis and judgment. This system not only improves the production efficiency, reduces the production cost, but also ensures the quality and safety of the wire harness 21.

[0066] Embodiment 2

[0067] As Figures 1 - 3 shown, different from Embodiment 1: In order to further improve the real-time performance and accuracy of the system, the processing module 31 also adds timestamps to the first feature vector and the second feature vector, and defines a time window to associate the relevant feature vectors. This association method can ensure that the system can consider the production timing relationship between the production equipment 11 and the wire harness 21 during analysis, thereby improving the accuracy of abnormal state detection.

[0068] Specifically, the processing module 31 adds a first timestamp Tc to the first feature vector, and the processing module 31 adds a second timestamp Tm to the second feature vector; the first timestamp Tc is used to indicate the time when the wire harness 21 is monitored during the production process of the production equipment 11; the second timestamp Tm is used to indicate the time when the production equipment 11 is monitored during the production process. In the specific implementation process, the processing module 31 defines the time window as W. When the first timestamp Tc of the first feature vector processed by the processing module 31 and the second timestamp Tm of the second feature vector satisfy: |Tc - Tm| ≤ W, the first feature vector and the second feature vector are associated.

[0069] In the specific implementation process, if the data of the first feature vector of the production equipment 11 and the second feature vector of the wire harness 21 after adding the first timestamp Tc and the second timestamp are:

[0070]

[0071] Among them, the first timestamp Tc is 10:00:00, the second timestamp Tm is 10:00:02; and the selected time window W is 5 seconds. Through the time correlation analysis of the present application, it is satisfied that ∣10:00:00 - 10:00:02∣ = 2 seconds ≤ 5 seconds. Thus, the first eigenvector and the second eigenvector pointed to by the above first timestamp Tc and the second timestamp Tm can be correlated.

[0072] For those that are the same as those in Embodiment 1, they will not be elaborated in this embodiment.

[0073] Embodiment 3

[0074] As Figures 1 - 3 shown, different from Embodiment 1: In order to further improve the abnormal states of the production equipment 11 and the wire harness 21 pointed to by the first eigenvector and the second eigenvector monitored in real time by the neural network unit 32 of the present application. Further, the neural network unit 32 includes a training set 321 and an input set 322. The training set 321 inputs the third eigenvector of the production equipment 11 in an abnormal state and / or the fourth eigenvector of the wire harness 21 in an abnormal state through an external device; among them, the feature type of the third eigenvector is the same as that of the first eigenvector, and the feature type of the fourth eigenvector is the same as that of the second eigenvector; the input set 322 is used to input the first eigenvector produced by the production equipment 11 in real time and the second eigenvector of the wire harness 21 produced by the production equipment 11 in real time.

[0075] The working principles of the training set 321 and the input set 322 of the above neural network unit 32 are as follows: The training set 321 helps the neural network unit 32 learn and identify abnormal features by inputting a large amount of known abnormal state data. During the training process, the neural network unit 32 will deeply analyze these abnormal feature vectors, extract key information, and establish a mapping relationship between the abnormal state and the feature vector. When the input set 322 receives the real-time first eigenvector and second eigenvector, the neural network unit 32 will use the established mapping relationship to quickly and accurately judge the abnormal state of these feature vectors. If the judgment result is an abnormal state, the system will immediately trigger an alarm and send the abnormal information to the host computer so that the operator can take measures to intervene in time. This design of the neural network unit 32 based on the training set 321 and the input set 322 not only improves the real-time performance and accuracy of the system, but also enhances the adaptive ability and robustness of the system, enabling it to better adapt to various complex production environments and wire harness 21 types.

[0076] Further, the neural network unit 32 judges the similarity between the first eigenvector and the third eigenvector, and the similarity between the second eigenvector and the fourth eigenvector through similarity analysis; the expression of the similarity analysis is:

[0077]

[0078] where S is the similarity value, V c is the first eigenvector, V m is the second eigenvector.

[0079] Specifically, the neural network unit 32 performs a similarity analysis on the first eigenvector and the third eigenvector; when the similarity value between the first eigenvector and the third eigenvector is greater than the first threshold, the neural network unit 32 determines that the production equipment 11 pointed to by the first eigenvector is in an abnormal state. At the same time, the neural network unit 32 performs a similarity analysis on the second eigenvector and the fourth eigenvector; when the similarity value between the second eigenvector and the fourth eigenvector is greater than the second threshold, the neural network unit 32 determines that the wire harness 21 pointed to by the second eigenvector is in an abnormal state. Thus, the system of the present application can more accurately identify and predict the abnormal states of the production equipment 11 and the wire harness 21 according to the abnormal states of the wire harness 21 and the production equipment 11, thereby reducing false alarms and missed alarms. In addition, this similarity analysis method can also help the system perform hierarchical processing on the abnormal states, and judge the severity of the abnormality according to the size of the similarity value, providing more accurate decision-making support for the operator. For example, when the similarity value between the first eigenvector and the third eigenvector is extremely high, it indicates that the production equipment 11 may have serious faults or abnormalities. At this time, the system can trigger a high-level alarm and give priority to sending relevant information to the operator to ensure that the problem can be processed in a timely manner. At the same time, the system can also continuously optimize and adjust the similarity threshold according to historical data and real-time data to improve the accuracy and reliability of abnormal state judgment.

[0080] Furthermore, the system further includes a host computer communicatively connected to the processing module 31. The processing module 31 outputs the anti-interference communication state of the wire harness 21 produced by the production equipment 11 pointed to by the first eigenvector by the neural network unit 32 and / or the safety state of the production equipment 11 corresponding to the wire harness 21 pointed to by the second eigenvector by the neural network unit 32 to the host computer.

[0081] For the rest that is the same as that in Embodiment 1, it will not be elaborated in this embodiment.

[0082] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A neural network-based anti-interference communication harness production safety supervision system, characterized in that: It comprises a first monitoring terminal (1), a second monitoring terminal (2), and a control terminal (3) connected to both the first monitoring terminal (1) and the second monitoring terminal (2); The first monitoring terminal (1) is used to monitor the real-time production status of the production equipment (11) in the production workshop and divide the production status data of the production equipment (11) into a first feature vector containing at least one feature type based on various features of the production equipment (11); The second monitoring terminal (2) is used to perform anti-interference communication monitoring on the wiring harness (21) produced in real time by the production equipment (11) and to divide the anti-interference communication data of the wiring harness (21) into a second feature vector containing at least one feature type; The control end (3) comprises a processing module (31) and a neural network unit (32) connected to the processing module (31); the processing module (31) is communicatively connected to the first monitoring terminal (1) and the second monitoring terminal (2) and transmits the first feature vector and the second feature vector to the neural network unit (32); The neural network unit (32) determines the anti-interference communication status of the wiring harness (21) produced by the production equipment (11) pointed to by the first feature vector through the first feature vector and / or the neural network unit (32) determines the safety status of the production equipment (11) corresponding to the wiring harness (21) pointed to by the second feature vector through the second feature vector.

2. According to the neural network-based anti-interference communication harness production safety supervision system of claim 1, it is characterized in that: The processing module (31) adds a first timestamp Tc to the first feature vector, and the processing module (31) adds a second timestamp Tm to the second feature vector; The first timestamp Tc is used to indicate the time when the wiring harness (21) is monitored during the production process of the production equipment (11); The second timestamp Tm is used to indicate the time when the production equipment (11) is monitored during the production process.

3. According to the neural network-based anti-interference communication harness production safety supervision system of claim 1, it is characterized in that: The processing module defines a time window as W. When the first timestamp Tc of the first feature vector processed by the processing module (31) and the second timestamp Tm of the second feature vector satisfy: |Tc-Tm|≤W, the first feature vector is associated with the second feature vector.

4. According to the neural network-based anti-interference communication harness production safety supervision system of claim 1, it is characterized in that: The neural network unit (32) includes a training set (321) and an input set (322), wherein the training set (321) inputs a third feature vector of the production equipment (11) in an abnormal state and / or a fourth feature vector of the wiring harness (21) in an abnormal state through an external device; wherein the feature type of the third feature vector is the same as the feature type of the first feature vector, and the fourth feature vector is the same as the feature type of the second feature vector; The input set (322) is used to input the first feature vector produced in real time by the production equipment (11) and the second feature vector of the wire harness (21) produced in real time by the production equipment (11).

5. The anti-interference communication harness production safety supervision system based on neural network according to claim 4 is characterized in that: The neural network unit (32) determines the similarity between the first feature vector and the third feature vector, and the similarity between the second feature vector and the fourth feature vector through similarity analysis; the expression of the similarity analysis is: Among them, S is the similarity value, V c is the first eigenvector, V m is the second eigenvector.

6. The neural network-based anti-interference communication harness production safety supervision system according to claim 5, characterized in that: The neural network unit (32) performs similarity analysis on the first feature vector and the third feature vector; When the similarity value between the first feature vector and the third feature vector is greater than a first threshold value, the neural network unit (32) determines that the production equipment (11) pointed to by the first feature vector is in an abnormal state.

7. The neural network-based anti-interference communication harness production safety supervision system according to claim 5, characterized in that: The neural network unit (32) performs similarity analysis on the second eigenvector and the fourth eigenvector; When the similarity value between the second eigenvector and the fourth eigenvector is greater than a second threshold value, the neural network unit (32) determines that the wiring harness (21) pointed to by the second eigenvector is in an abnormal state.

8. The anti-interference communication harness production safety supervision system based on neural network according to claim 1 is characterized in that: The feature type of the first feature vector is at least one of a signal-to-noise ratio, an electromagnetic interference level, a response time, and a power loss.

9. The neural network-based anti-interference communication harness production safety supervision system according to claim 1, characterized in that: The characteristic type of the second characteristic item is at least one of device temperature, output power, and working time.

10. The anti-interference communication harness production safety supervision system based on neural network according to claim 1, characterized in that: It also includes a host computer (4) communicatively connected to the processing module (31), and the processing module outputs to the host computer (4) the anti-interference communication status of the wiring harness (21) produced by the production equipment (11) pointed to by the first feature vector judged by the neural network unit (32) through the first feature vector and / or the safety status of the production equipment (11) corresponding to the wiring harness (21) pointed to by the second feature vector judged by the neural network unit (32) through the second feature vector.

Images