Equipment fault voiceprint recognition monitoring system and method based on cloud edge cooperation

Abstract

The invention discloses an equipment fault voiceprint recognition monitoring system and method based on cloud-side cooperation, and relates to the technical field of equipment fault monitoring, and the method comprises the steps that a cloud server receives a data transmission request sent by target edge equipment, the data transmission request comprises the data size of voiceprint data, and the data size of the voiceprint data is sent to the target edge equipment; the target edge device is one of a plurality of edge devices; determining a first bandwidth required for transmitting the voiceprint data based on the time delay and the data volume; judging whether the first bandwidth is smaller than the residual available bandwidth or not to obtain a first judgment result; if the first judgment result represents that the first bandwidth is smaller than or equal to the remaining available bandwidth, allocating the first bandwidth to the target edge device; and receiving the voiceprint data through the first bandwidth, and carrying out fault voiceprint recognition monitoring on the industrial equipment according to the voiceprint data. According to the method, the purposes of reducing the transmission delay time and improving the data transmission efficiency are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment fault monitoring, and in particular to a system and method for equipment fault voiceprint recognition and monitoring based on cloud-edge collaboration. Background Art

[0002] In industrial equipment fault monitoring scenarios, existing technologies often use a relatively fixed transmission mode for the transmission of equipment fault data. Typically, edge devices collect data from industrial equipment during operation and upload this data to the cloud, regardless of whether the industrial equipment is actually operating and generating valid fault diagnosis data. For example, for device sound signals, even if the sound is not useful for fault identification when the device is not operating, the edge device will still transmit this redundant audio data to the cloud. The cloud will then filter and analyze large amounts of invalid data in the hope of selecting data that can be used for fault diagnosis during the equipment's operating period.

[0003] However, existing technologies have significant drawbacks. On the one hand, invalid data during the device's operating hours is transmitted alongside valid data, squeezing the transmission space for critical data and increasing overall transmission latency. This can easily lead to network congestion, especially when monitoring multiple devices simultaneously, affecting the real-time nature of fault monitoring. On the other hand, the cloud consumes significant computing power to process redundant data, increasing data processing costs and fault identification delays. Furthermore, edge devices continuously collect and upload data, consuming significant energy and storage pressure, reducing operational stability and battery life (in the case of portable edge devices). This makes it impossible to efficiently adapt to the actual needs of dynamic and accurate transmission of device fault data. Summary of the Invention

[0004] The present application provides a device fault voiceprint recognition and monitoring system and method based on cloud-edge collaboration, which can reduce transmission delay time and further improve data transmission efficiency.

[0005] To achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application provides a device fault voiceprint recognition and monitoring system based on cloud-edge collaboration, the system comprising a cloud server and multiple edge devices; the data transmission between the multiple edge devices and the cloud server shares the same bandwidth; the cloud server is used to receive a data transmission request sent by a target edge device, the data transmission request including the data volume of the voiceprint data, and the target edge device is one of the multiple edge devices; the cloud server determines the first bandwidth required to transmit the voiceprint data based on the latency and data volume; the cloud server determines whether the first bandwidth is less than the remaining available bandwidth to obtain a first judgment result; if the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is allocated to the target edge device; the cloud server receives the voiceprint data through the first bandwidth, and then performs fault voiceprint recognition and monitoring on the industrial equipment based on the voiceprint data.

[0006] In some possible implementations, the cloud server determines whether the first bandwidth is less than the remaining available bandwidth to obtain a first judgment result; if the first judgment result indicates that the first bandwidth is greater than the remaining available bandwidth, a second bandwidth is allocated to the target edge device, and the second bandwidth is less than or equal to the remaining available bandwidth.

[0007] In some possible implementations, the cloud server is further configured to dynamically schedule, when allocating the second bandwidth to the target edge device, the second bandwidth to be allocated to the target edge device based on the fault identification priority of the voiceprint data; The dynamic scheduling of fault identification priorities based on voiceprint data includes: The cloud server pre-sets a priority level for industrial equipment fault voiceprint recognition scenarios; When allocating the second bandwidth, extract the fault identification priority corresponding to the voiceprint data transmitted by the target edge device. If it is the first priority, allocate the second bandwidth according to the first allocation method; if it is the second priority, allocate the second bandwidth according to the second allocation method; if it is the third priority, allocate the second bandwidth according to the third allocation method.

[0008] In some possible implementations, the target edge device divides the voiceprint data obtained from the industrial equipment into multiple data segments according to time series or frequency characteristics, and obtains a feature label for each data segment; the target edge device reports the feature labels of multiple data segments to the cloud server before transmission, and the cloud server dynamically allocates sub-bandwidths to data segments with different feature labels based on bandwidth usage; during the transmission process, the sub-bandwidth utilization of each data segment is evaluated in real time. If the utilization of the first sub-bandwidth is continuously lower than the first utilization threshold, the first sub-bandwidth is recovered and the bandwidth is reallocated.

[0009] In some possible implementations, the cloud server performs fault voiceprint recognition monitoring on industrial equipment based on the voiceprint data to obtain recognition results of the voiceprint data; the cloud server determines whether the recognition loss accuracy caused by bandwidth allocation exceeds a loss threshold based on the recognition results of the voiceprint data; if the recognition loss accuracy exceeds the loss threshold, the bandwidth adjustment process is triggered in reverse, and a preset multiple of bandwidth is reserved for subsequent transmission of voiceprint data of the same type; at the same time, based on the recognition results of historical bandwidth allocation, a dynamic bandwidth prediction model is trained, and bandwidth is pre-allocated for the voiceprint data to be transmitted according to the training results.

[0010] In some possible implementations, the cloud server is also used to monitor the transmission progress of multiple edge devices in real time. When a first-priority data transmission request occurs, the third-priority data transmission can be interrupted and the bandwidth can be reallocated.

[0011] In some possible implementations, after collecting the initial voiceprint data of the industrial equipment, the target edge device performs noise filtering on the voiceprint data based on wavelet transform to obtain voiceprint data; wherein the filtering intensity of the noise filtering is dynamically adjusted according to the operating status of the industrial equipment; the target edge device divides the voiceprint data into multiple data segments according to time series or frequency characteristics, and sets feature overlapping areas for adjacent data segments; the target edge device transmits the multiple data segments to the cloud server.

[0012] In some possible implementations, when the cloud server manages multiple edge devices, the remaining available bandwidth and device failure risk levels of the multiple edge devices are summarized in real time; if the first-priority voiceprint data transmission of the target edge device requires additional bandwidth, and there is idle bandwidth in multiple edge devices other than the target edge device, cross-regional bandwidth scheduling is triggered, and the idle bandwidth is temporarily allocated to the target edge device; after the transmission is completed, the cross-regional allocated bandwidth is automatically recovered and the original regional bandwidth allocation benchmark is restored.

[0013] In a second aspect, the present application provides a device fault voiceprint recognition and monitoring method based on cloud-edge collaboration, which is applied to a cloud server; the method includes: receiving a data transmission request sent by a target edge device, the data transmission request including the data volume of the voiceprint data, the target edge device being one of the multiple edge devices; Determining a first bandwidth required for transmitting the voiceprint data based on the time delay and the data volume; Determine whether the first bandwidth is less than the remaining available bandwidth, and obtain a first determination result; If the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, allocating the first bandwidth to the target edge device; The voiceprint data is received via the first bandwidth, and fault voiceprint recognition and monitoring of industrial equipment is performed based on the voiceprint data.

[0014] In a third aspect, the present application provides a computing device, including a memory and a processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as described in any one of the first aspects.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program for executing the method as described in any one of the first aspects.

[0016] In a fifth aspect, the present application provides a computer program product, which includes one or more computer instructions. When the computer instructions are executed by a computer, the computer executes the method as described in any one of the first aspects.

[0017] It can be seen from the above technical solution that this application has at least the following beneficial effects: In the present application, a cloud server receives a data transmission request sent by a target edge device, the data transmission request includes the amount of voiceprint data, and the target edge device is one of multiple edge devices; based on the delay and the amount of data, the first bandwidth required for transmitting the voiceprint data is determined; it is judged whether the first bandwidth is less than the remaining available bandwidth to obtain a first judgment result; if the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is allocated to the target edge device; the voiceprint data is received through the first bandwidth, and then the industrial equipment is subjected to fault voiceprint recognition and monitoring based on the voiceprint data. In the field of industrial equipment fault monitoring, the existing technology often adopts a relatively fixed transmission mode, and the edge device will upload the collected data to the cloud regardless of whether the industrial equipment is in a valid fault diagnosis data generation state. It can be seen that the device fault voiceprint recognition and monitoring system based on cloud-edge collaboration provided by the present application determines the required bandwidth according to the delay and the amount of voiceprint data through the cloud server, dynamically allocates bandwidth, and performs refined scheduling in combination with fault identification priority, data segment feature tags, etc., thereby achieving the purpose of reducing transmission delay time and improving data transmission efficiency.

[0018] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution or beneficial effect is included in at least one embodiment. Therefore, the description of a technical feature, technical solution or beneficial effect in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of an application scenario provided in an embodiment of the present application; Figure 2 A flow chart of a device fault voiceprint recognition and monitoring method based on cloud-edge collaboration provided in an embodiment of the present application; Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The terms "first", "second" and "third" in this application specification and the accompanying drawings are used to distinguish different objects rather than to limit a specific order.

[0021] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0022] Currently, existing technologies that statically allocate bandwidth cause invalid data from the device's operating hours to be transmitted alongside valid data during device data transmission. This not only squeezes the transmission space for critical data, but also, due to the fixed bandwidth allocation and lack of dynamic adjustment, fails to prioritize critical data, leading to increased overall transmission latency. This can easily cause network congestion when monitoring multiple devices simultaneously, impacting the real-time nature of fault monitoring. It also requires the cloud to expend significant computing power to process redundant data, increasing data processing costs and fault identification delays. Meanwhile, edge devices continuously collect and upload data, placing significant pressure on their own energy consumption and storage, reducing the stability and endurance of device operation, and failing to efficiently adapt to the actual needs of dynamic and accurate transmission of device fault data.

[0023] In view of this, an embodiment of the present application provides a device fault voiceprint recognition and monitoring system based on cloud-edge collaboration, in which the cloud server receives a data transmission request sent by a target edge device, the data transmission request includes the data volume of the voiceprint data, and the target edge device is one of multiple edge devices; based on the delay and the data volume, the first bandwidth required for transmitting the voiceprint data is determined; it is judged whether the first bandwidth is less than the remaining available bandwidth to obtain a first judgment result; if the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is allocated to the target edge device; the voiceprint data is received through the first bandwidth, and then the industrial equipment is subjected to fault voiceprint recognition and monitoring based on the voiceprint data. It can be seen that the device fault voiceprint recognition and monitoring system based on cloud-edge collaboration provided by the present application determines the required bandwidth according to the delay and the voiceprint data volume through the cloud server, dynamically allocates the bandwidth, and performs refined scheduling in combination with the fault recognition priority, data segment feature tags, etc., thereby achieving the purpose of reducing transmission delay time and improving data transmission efficiency.

[0024] In order to make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are introduced below with reference to the accompanying drawings. Figure 1 As shown in the figure, this figure is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0025] In this application scenario, there are three edge devices, three industrial devices, and one cloud server 4. The edge devices are nodes close to the industrial devices and are responsible for data collection and initial processing, while the cloud server is responsible for data aggregation, storage, and further analysis. The three edge devices include edge device 1, edge device 2, and target edge device 3. The three industrial devices include industrial devices 11, 12, and 13.

[0026] Edge device 1 is used to receive voiceprint data from industrial equipment 11, edge device 2 is used to receive voiceprint data from industrial equipment 12, and target edge device 3 is used to receive voiceprint data from industrial equipment 13. The three edge devices transmit the received voiceprint data to cloud server 4. Voiceprint data is like the sound fingerprint of industrial equipment, which can reflect the operating status of the equipment. For example, the voiceprint characteristics of different states such as normal operation and early stage of failure are different.

[0027] After the three edge devices collect the voiceprint data of their corresponding industrial equipment, they will transmit this voiceprint data to the cloud server 4. In this way, the cloud server can centrally manage and analyze the voiceprint data of multiple industrial equipment. For example, by comparing voiceprint anomalies, it can determine whether the equipment is faulty and predict maintenance needs, etc., and build an industrial Internet of Things data link from industrial equipment data collection, to edge processing, and then to cloud aggregation and analysis.

[0028] The present application provides a device fault voiceprint recognition and monitoring system based on cloud-edge collaboration. The cloud server determines the required bandwidth according to the latency and the amount of voiceprint data, dynamically allocates the bandwidth, and performs refined scheduling based on fault identification priority, data segment feature tags, etc., thereby achieving the purpose of reducing transmission delay time and improving data transmission efficiency.

[0029] In order to make the technical solution of this application clearer and easier to understand, the following describes a device fault voiceprint recognition and monitoring system based on cloud-edge collaboration provided by an embodiment of this application in combination with the above application scenarios. In this embodiment of the application, the system includes: The equipment fault voiceprint recognition and monitoring system includes a cloud server and multiple edge devices; the data transmission between multiple edge devices and the cloud server shares the same bandwidth; among them, the cloud server has powerful data processing, storage and computing capabilities, and is used to coordinate the management and analysis of data uploaded by edge devices; the edge device is deployed close to the industrial equipment, responsible for collecting and preliminarily processing voiceprint data and interacting with the cloud server.

[0030] The cloud server is used to receive a data transmission request from a target edge device, which includes the amount of voiceprint data. The target edge device is one of multiple edge devices. The specific steps are as follows: the cloud server receives the data transmission request from the target edge device, which represents the edge device among the multiple edge devices that is currently receiving voiceprint data from industrial equipment and initiating the data transmission request. The data transmission request includes the amount of voiceprint data. For example, if the target edge device detects that the industrial equipment has started running and needs to transmit the working sound data to the cloud server, it will send a data transmission request including the transmission of 100MB of voiceprint data.

[0031] The cloud server determines the first bandwidth required to transmit voiceprint data based on latency and data volume. Latency refers to the time delay in transmitting voiceprint data from the target edge device to the cloud server, and the required first bandwidth refers to the ideal bandwidth that the target edge device can use to transmit voiceprint data smoothly and without congestion. The cloud server calculates the first bandwidth required for transmitting voiceprint data based on the data volume and the allowable latency of data transmission. For example, if you want to transmit 100MB of voiceprint data within 1 second, considering the network characteristics, you may calculate that 100Mbps of bandwidth is required, which is the first bandwidth. If you allow 3 seconds to transmit, the first bandwidth can be less than 100Mbps.

[0032] The cloud server determines whether the first bandwidth is less than the remaining available bandwidth, and obtains a first determination result; If the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is allocated to the target edge device; if the first judgment result indicates that the first bandwidth is greater than the remaining available bandwidth, the second bandwidth is allocated to the target edge device, and the second bandwidth is less than or equal to the remaining available bandwidth. The specific steps are as follows: The remaining available bandwidth refers to the total bandwidth minus the bandwidth allocated to other edge devices for transmission and the bandwidth required by the cloud server to transmit requests to other edge devices, that is, the remaining allocable portion after the fixed reserved bandwidth; the second bandwidth refers to the bandwidth that can actually be allocated and does not exceed the remaining available bandwidth when the first bandwidth exceeds the remaining available bandwidth. Comparing the first bandwidth and the remaining available bandwidth, if the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is directly allocated to the target edge device; if the first bandwidth is greater than the remaining available bandwidth, the second bandwidth is allocated that is less than or equal to the remaining available bandwidth to ensure that bandwidth allocation can be achieved within the existing network resources. In some embodiments, the total bandwidth is 100Mbps, 60Mbps has been used by other edge devices and the fixed reserved bandwidth, and 40Mbps remains. If the first bandwidth is calculated to be 30Mbps, 30Mbps is directly allocated; if the first bandwidth is 50Mbps, only a second bandwidth of less than or equal to 40Mbps can be allocated, such as 40Mbps.

[0033] Specifically, the cloud server is used to dynamically allocate the second bandwidth to the target edge device based on the fault identification priority of the voiceprint data. This includes: the cloud server pre-sets a priority hierarchy for the industrial equipment fault voiceprint identification scenario; the priority hierarchy is the urgency and importance level pre-set by the cloud server for the industrial equipment fault voiceprint identification scenario, which determines which edge device the bandwidth allocation is tilted towards. The cloud server pre-sets the priority hierarchy for the scenario of using voiceprint to identify equipment failures. For example, the cloud server sets the priority hierarchy in advance for the scenario of using voiceprint to identify equipment failures. For example, abnormal noise during equipment startup (which may be a precursor to a serious fault) is set as the first priority, and minor noise during normal equipment operation is set as the third priority.

[0034] When allocating the second bandwidth, the fault identification priority corresponding to the voiceprint data transmitted by the target edge device is extracted. If it is the first priority, the second bandwidth is allocated according to the first allocation method; if it is the second priority, the second bandwidth is allocated according to the second allocation method; if it is the third priority, the second bandwidth is allocated according to the third allocation method. Among them, the first allocation method is a strategy to provide as much bandwidth as possible to ensure fast and stable transmission, such as prioritizing the allocation of most of the remaining available bandwidth; the second allocation method is to allocate less bandwidth than the first priority to ensure basic transmission; the third allocation method is to allocate less bandwidth to meet basic transmission requirements. For example, if the remaining available bandwidth is 40Mbps, the first priority data may be transmitted at 20Mbps; the second priority data at 15Mbps; and the third priority data at 5Mbps, so that critical fault data can be transmitted first and efficiently.

[0035] Specifically, if industrial equipment 11 is a stamping press in an automobile factory, abnormal metal friction noise during startup could indicate mold misalignment or loose components, which could cause a production line shutdown in severe cases. This is prioritized first, requiring the cloud server to prioritize high bandwidth allocation when transmitting data from edge device 1 (the edge device connected to the stamping press), ensuring data is transmitted back within seconds for analysis. The slight airflow noise during the equipment's idling and warm-up phase (a normal startup process) is prioritized third, and bandwidth allocation can be temporarily deferred.

[0036] Specifically, if industrial equipment 11 is an assembly line robot, and edge device 1 collects the friction soundprint of a jammed robot joint (this soundprint data is assigned the first priority, as this fault could cause material jams on the production line and affect production), while edge device 12 (connected to a stamping press) simultaneously collects the slight mechanical sound of normal operation (this soundprint data is assigned the third priority). In this case, the cloud server will prioritize allocating the second bandwidth to edge device 1, ensuring that the assembly line robot's fault soundprint data is uploaded and analyzed first, while the normal data from the stamping press is temporarily suspended.

[0037] Specifically, if the industrial equipment 13 is a chemical reactor, when the target edge device 3 collects voiceprint data, if an abnormal sound of motor startup is identified during the startup phase (this voiceprint data is the first priority and is a precursor to a serious fault), the cloud server will immediately allocate a second bandwidth to the edge device 3. The second bandwidth is the maximum available bandwidth that the cloud server can allocate, so that the fault warning data can be uploaded quickly; the bandwidth allocation in the stable operation phase is reduced to a minimum. For example, if there is only a slight cooling fan sound of the equipment, the voiceprint data is the fourth priority and only basic data transmission is maintained; when the reactor starts to unload and the equipment load suddenly changes, if an abnormal pipeline vibration soundprint occurs (this voiceprint data is the second priority and may be a material blockage), the cloud server will dynamically increase the bandwidth to ensure priority analysis of abnormal data.

[0038] The purpose of setting priority levels is to classify the urgency of voiceprint analysis needs for different fault hazards and equipment operation stages. These layers directly determine to whom the cloud server prioritizes bandwidth allocation when multiple edge devices transmit voiceprint data simultaneously, enabling faster transmission and analysis of critical data. For factory operations and maintenance, prioritizing the transmission and analysis of high-risk fault voiceprints can detect early warning signs of equipment failure. For example, for a top-priority event like an abnormal sound during startup of a stamping machine, data transmission and fault diagnosis can be completed within 10 seconds. Compared with the traditional method of waiting for a fault to occur and then handling it, this can reduce unplanned downtime losses by over 80%. For resource utilization, dynamic bandwidth scheduling can avoid the waste of fixed bandwidth allocation regardless of data criticality, allowing limited network resources to be precisely allocated to the most needed fault identification scenarios. This is particularly suitable for smart factories with multiple production lines and multiple devices running concurrently. For load changes in continuously operating equipment, such as the blast furnace blast equipment in a steel plant, the sudden appearance of high-frequency vibration soundprints during full load operation may indicate bearing overload or impeller deformation. Without timely intervention, this may lead to downtime or explosion risks. Therefore, this voiceprint data is set as the top priority to prioritize data transmission for target edge device 3 (the docking blast equipment). Compare the smooth transition voiceprints of the device switching from low load to full load, set the voiceprint data as the third priority, and bandwidth allocation can be postponed.

[0039] In some embodiments, the target edge device divides the voiceprint data acquired from industrial equipment into multiple data segments based on time series or frequency characteristics, and obtains a feature label for each data segment. Time series refers to the division based on the chronological order of voiceprint data collection, such as dividing voiceprint data within a minute into 10-second segments. Frequency characteristics refer to the division based on the different frequency components in the voiceprint data, such as separating high-frequency and low-frequency voiceprint data into segments. Feature labels are identifiers assigned to each data segment, marking the key characteristics of this data segment for cloud-based identification. The target edge device divides the collected industrial equipment voiceprint data into multiple segments either by time or by frequency components, and then assigns a feature label to each segment, such as [Time: 0-10 seconds, Frequency: High Frequency, Equipment: Machine Tool A].

[0040] Before transmitting voiceprint data, the target edge device reports the characteristic tags of multiple data segments to the cloud server. The cloud server dynamically allocates sub-bandwidths to data segments with different characteristic tags based on bandwidth usage. Sub-bandwidth is the total bandwidth allocated to the edge device, which is further subdivided into small channels for each data segment, allowing different types of voiceprint data segments to be transmitted in parallel and in an orderly manner. During the transmission process, the sub-bandwidth utilization of each data segment is evaluated in real time. If the utilization of the first sub-bandwidth is continuously lower than the first utilization threshold, the first sub-bandwidth is recovered and the bandwidth is reallocated. The first utilization threshold is used to determine whether the sub-bandwidth is idle or inefficiently used. For example, a sub-bandwidth utilization rate below 30% is considered inefficient.

[0041] On the one hand, segmenting by time series can capture the operating status of equipment at different times. For example, voiceprint data from stages where industrial equipment takes 0-10 seconds to start up, maintains stable operation for 10-20 seconds, and changes in load for 20-30 seconds can be used to accurately analyze the health status of each stage. Time series segmentation allows the operating status of equipment to be traced back, allowing operation and maintenance personnel to review when the equipment anomalies occurred and the changes in status before and after the anomalies, assisting in optimizing operation and maintenance strategies, such as adjusting equipment startup processes and maintenance cycles. On the other hand, segmenting by frequency characteristics: high-frequency voiceprint data is often associated with wear on industrial equipment components (such as abnormal bearing noise), while low-frequency voiceprint data corresponds to structural vibration. Separate analysis can quickly locate the source of the fault and improve diagnostic accuracy. Splitting continuous massive voiceprint data into small segments can also reduce the amount of data processed in the cloud, reduce computing resource consumption, increase data processing speed, and make fault identification and status monitoring more timely.

[0042] Feature tags mark key characteristics, and cloud servers can quickly identify abnormal data segments. If the feature tag contains "high frequency, equipment: machine tool A, time: startup phase", combined with the historical fault database, it can warn that the high-frequency abnormal noise when machine tool A is started may be a bearing failure, so as to achieve early maintenance and avoid downtime losses. Standardized feature tags also allow cloud servers to quickly understand the meaning of data uploaded by edge devices without the need for complex decoding, improve the efficiency of cloud-edge collaboration, and make it smoother for the cloud to uniformly manage data from multiple edge devices and multiple industrial equipment. Standardized data segmentation and labeling provide high-quality data for building equipment voiceprint models and training AI fault recognition algorithms, and promote the development of industrial operation and maintenance towards predictive and intelligent development. For example, based on a large amount of labeled data, training models can realize automatic fault classification and prediction.

[0043] The cloud server monitors fault voiceprint recognition of industrial equipment based on voiceprint data and obtains the recognition results of the voiceprint data. Based on the recognition results of the voiceprint data, the cloud server determines whether the recognition loss accuracy caused by bandwidth allocation exceeds the loss threshold. The recognition loss accuracy refers to the degree to which the fault recognition accuracy and precision are reduced due to insufficient bandwidth, incomplete data transmission, and loss. The loss threshold is the maximum degree of recognition accuracy reduction allowed. If it is exceeded, the bandwidth must be adjusted.

[0044] If the recognition loss accuracy exceeds the loss threshold, the bandwidth adjustment process is triggered in reverse, prioritizing the reservation of a preset multiple of bandwidth for subsequent voiceprint data transmission of the same type. At the same time, based on the recognition results of historical bandwidth allocation, a dynamic bandwidth prediction model is trained, and bandwidth is pre-allocated for voiceprint data to be transmitted based on the training results. The preset multiple is to ensure the subsequent transmission of critical data, and the bandwidth ratio is reserved in advance, for example, reserving 2 times the current bandwidth required for subsequent data of the same type. The dynamic bandwidth prediction model analyzes historical bandwidth allocation, recognition results, and other data to learn patterns and predict the bandwidth required for future transmission.

[0045] In some embodiments, the cloud server is also used to monitor the transmission progress of multiple edge devices in real time. When a data transmission request of the first priority occurs, the data transmission of the third priority can be interrupted and the bandwidth can be reallocated. By monitoring the transmission progress of edge devices in real time, when there is a voiceprint data transmission request of the first priority, the voiceprint data transmission of the third priority can be interrupted and the bandwidth can be reallocated, so that key fault warning data can be uploaded to the cloud in priority and in a timely manner. The cloud server can obtain high-value data as soon as possible, buy time for rapid fault diagnosis and emergency processing, reduce the risk of equipment failure expansion caused by delayed key data transmission, and reduce production line downtime losses. Moreover, the cloud server no longer allocates bandwidth in a fixed manner, but dynamically schedules it according to the priority of voiceprint data to avoid long-term occupation of bandwidth resources by low-value data, improve the utilization efficiency of overall network resources in industrial equipment status monitoring scenarios, and allow limited bandwidth to accurately serve high-priority, high-value data transmission needs.

[0046] In some embodiments, after collecting initial voiceprint data from industrial equipment, the target edge device performs noise filtering on the voiceprint data based on wavelet transform to obtain voiceprint data. The noise filtering intensity is dynamically adjusted according to the operating status of the industrial equipment. The target edge device divides the voiceprint data into multiple data segments based on time series or frequency characteristics, and sets feature overlap areas for adjacent data segments. The target edge device transmits the multiple data segments to the cloud server. The purpose of setting feature overlap areas is to avoid the loss of edge features of data segments, achieve data structured management, ensure feature integrity, facilitate in-depth mining of equipment status from the time series and frequency dimensions in the cloud, and provide more reliable data support for fault diagnosis and predictive maintenance.

[0047] The specific steps are as follows: After the edge device collects the initial voiceprint data of the industrial equipment, it uses wavelet transform to filter the noise and obtain clean voiceprint data. Moreover, the filtering intensity is not fixed, and it will depend on the current state of the industrial equipment. For example, when the noise is loud during startup, the filtering intensity is increased; when the noise is low during stable operation, the filtering intensity is decreased. Wavelet transform is a signal processing method that can separate the useful signal and noise in the voiceprint, retaining the useful ones and filtering out the noise; filtering intensity refers to the strength of filtering the noise, such as how much low-frequency / high-frequency noise is filtered out, and is adjusted according to the operating status of the equipment. The feature overlap area refers to the overlapping part of two adjacent data segments to avoid cutting the voiceprint data too tightly, resulting in the loss of key features during segmentation.

[0048] After receiving the voiceprint data through the allocated first bandwidth (or adjusted bandwidth), the cloud server uses this data to perform fault voiceprint recognition and monitoring on industrial equipment to determine whether the equipment has faults and the type of fault, completing a complete closed loop from data transmission to fault diagnosis.

[0049] The cloud server receives the voiceprint data through the first bandwidth, and then performs fault voiceprint recognition and monitoring on the industrial equipment based on the voiceprint data.

[0050] Based on the above content, the cloud server receives a data transmission request sent by the target edge device, the data transmission request includes the data volume of the voiceprint data, and the target edge device is one of multiple edge devices; based on the delay and the data volume, the first bandwidth required for transmitting the voiceprint data is determined; it is judged whether the first bandwidth is less than the remaining available bandwidth to obtain a first judgment result; if the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, the first bandwidth is allocated to the target edge device; the voiceprint data is received through the first bandwidth, and then the industrial equipment is subjected to fault voiceprint recognition and monitoring based on the voiceprint data. The device fault voiceprint recognition and monitoring system based on cloud-edge collaboration provided in this application determines the required bandwidth according to the delay and the voiceprint data volume through the cloud server, dynamically allocates the bandwidth, and performs refined scheduling in combination with the fault recognition priority, data segment feature tags, etc., thereby achieving the purpose of reducing transmission delay time and improving data transmission efficiency.

[0051] The present application also provides a device fault voiceprint recognition and monitoring method based on cloud-edge collaboration, such as Figure 2 As shown in the figure, this figure is a flow chart of a device fault voiceprint recognition and monitoring method based on cloud-edge collaboration provided by an embodiment of the present application. The method is applied to a cloud server and includes: S201: Receive a data transmission request sent by a target edge device.

[0052] The data transmission request includes the data volume of the voiceprint data, and the target edge device is one of the multiple edge devices; S202: Determine a first bandwidth required for transmitting voiceprint data based on the time delay and the data volume.

[0053] S203: Determine whether the first bandwidth is less than the remaining available bandwidth, and obtain a first determination result.

[0054] If the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, executing S204; If the first judgment result indicates that the first bandwidth is greater than the remaining available bandwidth, S206 is executed.

[0055] S204: Allocate a first bandwidth to the target edge device.

[0056] S205: Receive voiceprint data via the first bandwidth, and then perform fault voiceprint recognition and monitoring on the industrial equipment based on the voiceprint data.

[0057] S206: Allocate a second bandwidth to the target edge device, where the second bandwidth is less than or equal to the remaining available bandwidth.

[0058] After executing S206 , the second bandwidth is determined as the first bandwidth, and then S204 is executed.

[0059] In some possible implementations, the method further includes: dynamically scheduling, when allocating the second bandwidth to the target edge device, the cloud server based on the fault identification priority of the voiceprint data; The dynamic scheduling of fault identification priorities based on voiceprint data includes: The cloud server pre-sets a priority level for industrial equipment fault voiceprint recognition scenarios; When allocating the second bandwidth, extract the fault identification priority corresponding to the voiceprint data transmitted by the target edge device. If it is the first priority, allocate the second bandwidth according to the first allocation method; if it is the second priority, allocate the second bandwidth according to the second allocation method; if it is the third priority, allocate the second bandwidth according to the third allocation method.

[0060] In some possible implementations, the method is also applied to a target edge device, and the method includes: the target edge device divides the voiceprint data obtained from the industrial equipment into multiple data segments according to time series or frequency characteristics, and obtains a feature label for each data segment; the target edge device reports the feature labels of multiple data segments to the cloud server before transmission, and the cloud server dynamically allocates sub-bandwidth to data segments with different feature labels based on bandwidth usage; during the transmission process, the sub-bandwidth utilization of each data segment is evaluated in real time. If the utilization of the first sub-bandwidth is continuously lower than the first utilization threshold, the first sub-bandwidth is recovered and the bandwidth is reallocated.

[0061] In some possible implementations, the method further includes: performing fault voiceprint recognition monitoring on industrial equipment based on the voiceprint data to obtain recognition results of the voiceprint data; the cloud server determines whether the recognition loss accuracy caused by bandwidth allocation exceeds a loss threshold based on the recognition results of the voiceprint data; if the recognition loss accuracy exceeds the loss threshold, the bandwidth adjustment process is reversely triggered to preferentially reserve a preset multiple of bandwidth for subsequent transmission of voiceprint data of the same type; at the same time, based on the recognition results of historical bandwidth allocation, a dynamic bandwidth prediction model is trained, and bandwidth is pre-allocated for the voiceprint data to be transmitted according to the training results.

[0062] In some possible implementations, the method further includes: monitoring the transmission progress of multiple edge devices in real time, and when a data transmission request of the first priority level occurs, interrupting the data transmission of the third priority level and reallocating the bandwidth.

[0063] In some possible implementations, the method is also applied to a target edge device, and the method includes: after collecting the initial voiceprint data of the industrial equipment, the target edge device performs noise filtering on the voiceprint data based on wavelet transform to obtain the voiceprint data; wherein the filtering intensity of the noise filtering is dynamically adjusted according to the operating status of the industrial equipment; the target edge device divides the voiceprint data into multiple data segments according to time series or frequency characteristics, and sets feature overlapping areas for adjacent data segments; the target edge device transmits the multiple data segments to the cloud server.

[0064] In some possible implementations, the method further includes: when the cloud server manages multiple edge devices, summarizing the remaining available bandwidth and device failure risk levels of the multiple edge devices in real time; if the first-priority voiceprint data transmission of the target edge device requires additional bandwidth, and there is idle bandwidth in multiple edge devices other than the target edge device, cross-regional bandwidth scheduling is triggered to temporarily allocate the idle bandwidth to the target edge device; after the transmission is completed, the cross-regional allocated bandwidth is automatically recovered and the original regional bandwidth allocation benchmark is restored.

[0065] The present application also provides a computing device. Figure 3 As shown, this figure is a schematic diagram of a computing device provided by an embodiment of the present application, wherein the computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0066] The bus 401 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0067] The processor 402 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0068] The communication interface 403 is used for external communication. For example, when the computing device is a first switch, the communication interface 403 can be used for communication between the first switch and the first user terminal, or between the first switch and the second switch.

[0069] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0070] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned device fault voiceprint recognition and monitoring method based on cloud-edge collaboration.

[0071] Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the aforementioned device fault voiceprint recognition and monitoring method based on cloud-edge collaboration.

[0072] The present application also provides a computer program product comprising one or more computer instructions that, when loaded and executed on a computing device, fully or partially generate the process or function described in the present application.

[0073] The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0074] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods for device fault voiceprint recognition and monitoring based on cloud-edge collaboration. The computer program product can be a software installation package. When any of the aforementioned methods for device fault voiceprint recognition and monitoring based on cloud-edge collaboration is needed, the computer program product can be downloaded and executed on the computer.

[0075] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0076] The above description is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A device fault voiceprint recognition and monitoring system based on cloud-edge collaboration, characterized by: The system includes a cloud server and multiple edge devices; data transmission between the multiple edge devices and the cloud server shares the same bandwidth; The cloud server is configured to receive a data transmission request sent by a target edge device, the data transmission request including the data volume of the voiceprint data, and the target edge device is one of the multiple edge devices; The cloud server is configured to determine a first bandwidth required for transmitting the voiceprint data based on latency and data volume; The cloud server is configured to determine whether the first bandwidth is less than the remaining available bandwidth, and obtain a first determination result; If the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, allocating the first bandwidth to the target edge device; The cloud server is configured to receive the voiceprint data via the first bandwidth, and then perform fault voiceprint recognition and monitoring on the industrial equipment based on the voiceprint data.

2. The system according to claim 1, wherein: The cloud server is configured to allocate a second bandwidth to the target edge device if the first judgment result indicates that the first bandwidth is greater than the remaining available bandwidth, and the second bandwidth is less than or equal to the remaining available bandwidth.

3. The system according to claim 2, characterized in that The cloud server is further configured to dynamically schedule the second bandwidth allocation to the target edge device based on the fault identification priority of the voiceprint data; The dynamic scheduling of fault identification priorities based on voiceprint data includes: The cloud server pre-sets a priority level for industrial equipment fault voiceprint recognition scenarios; When allocating the second bandwidth, extract the fault identification priority corresponding to the voiceprint data transmitted by the target edge device. If it is the first priority, allocate the second bandwidth according to the first allocation method; if it is the second priority, allocate the second bandwidth according to the second allocation method; if it is the third priority, allocate the second bandwidth according to the third allocation method.

4. The system according to any one of claims 1 to 3, characterized in that: The target edge device divides the voiceprint data obtained from the industrial equipment into multiple data segments according to time series or frequency characteristics, and obtains a feature label for each data segment; The target edge device reports characteristic tags of multiple data segments to the cloud server before transmission, and the cloud server dynamically allocates sub-bandwidth to data segments with different characteristic tags based on bandwidth usage; During the transmission process, the sub-bandwidth utilization of each data segment is evaluated in real time. If the first sub-bandwidth utilization is continuously lower than the first utilization threshold, the first sub-bandwidth is recovered and the bandwidth is reallocated.

5. The system according to claim 4, characterized in that The cloud server performs fault voiceprint recognition monitoring on the industrial equipment according to the voiceprint data to obtain recognition results of the voiceprint data; The cloud server determines, based on the recognition result of the voiceprint data, whether the recognition loss accuracy caused by bandwidth allocation exceeds a loss threshold; If the recognition loss accuracy exceeds the loss threshold, the bandwidth adjustment process is triggered in reverse, and a preset multiple of bandwidth is reserved for subsequent voiceprint data transmission of the same type; Based on the recognition results of historical bandwidth allocation, a dynamic bandwidth prediction model is trained, and bandwidth is pre-allocated for the voiceprint data that needs to be transmitted according to the training results.

6. The system according to claim 3, wherein: The cloud server is also used to monitor the transmission progress of multiple edge devices in real time. When a data transmission request of the first priority occurs, the data transmission of the third priority can be interrupted and the bandwidth can be reallocated.

7. The system according to claim 4, wherein: After collecting the initial voiceprint data of the industrial equipment, the target edge device performs noise filtering on the voiceprint data based on wavelet transform to obtain voiceprint data; wherein the filtering intensity of the noise filtering is dynamically adjusted according to the operating status of the industrial equipment; The target edge device divides the voiceprint data into multiple data segments according to time series or frequency characteristics, and sets feature overlapping areas for adjacent data segments; The target edge device transmits multiple data segments to the cloud server.

8. The system according to claim 3, wherein: When the cloud server manages multiple edge devices, it aggregates the remaining available bandwidth and device failure risk levels of the multiple edge devices in real time; If the first-priority voiceprint data transmission of the target edge device requires additional bandwidth, and multiple edge devices other than the target edge device have idle bandwidth, cross-region bandwidth scheduling is triggered to temporarily allocate the idle bandwidth to the target edge device; After the transmission is completed, the cross-regional bandwidth will be automatically recovered and the original regional bandwidth allocation benchmark will be restored.

9. A device fault voiceprint recognition and monitoring method based on cloud-edge collaboration, characterized in that: The method is applied to a cloud server; the method comprises: receiving a data transmission request sent by a target edge device, the data transmission request including the data volume of the voiceprint data, the target edge device being one of the multiple edge devices; Determining a first bandwidth required for transmitting the voiceprint data based on the time delay and the data volume; Determine whether the first bandwidth is less than the remaining available bandwidth, and obtain a first determination result; If the first judgment result indicates that the first bandwidth is less than or equal to the remaining available bandwidth, allocating the first bandwidth to the target edge device; The voiceprint data is received via the first bandwidth, and fault voiceprint recognition and monitoring of industrial equipment is performed based on the voiceprint data.

10. The method according to claim 9, characterized in that The method further comprises: If the first judgment result indicates that the first bandwidth is greater than the remaining available bandwidth, a second bandwidth is allocated to the target edge device, where the second bandwidth is less than or equal to the remaining available bandwidth.

Images