A space equipment group operation status monitoring system with autonomous learning

Abstract

The present invention discloses a spatial equipment group operation status monitoring system with autonomous learning, comprising a sound status analysis module and a temperature status analysis module. The sound status analysis module is used to judge the operation status of the equipment according to the operation sound of the equipment, and the temperature status analysis module is used to judge the operation status of the equipment according to the temperature of the equipment operation environment. The sound status analysis module comprises a signal acquisition module, a feature extraction module, a sound feature library, a fault detection module, an autonomous learning module, and a sound analysis module. The feature extraction module and the fault detection module are electrically connected to the sound feature library, the signal acquisition module is electrically connected to the fault location module, the autonomous learning module is electrically connected to the sound feature library and the fault detection module, and the sound analysis module is electrically connected to the fault detection module. The present invention has the characteristics of strong practicality.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation monitoring, and in particular to an operating status monitoring system for a space equipment group with autonomous learning. Background Art

[0002] When existing equipment is running, sensors are usually installed on the actuators to detect its operation. This detection method requires huge manpower and material resources, and the installation structure of the sensor involves the improvement of the machine itself, which is bound to face the upgrading of equipment. Some small factories cannot afford the installation cost of a large number of sensors, and often rely on the old masters to listen to the equipment to judge whether there is a fault, which is not practical.

[0003] At the same time, existing detection systems often uniformly use high-resolution sound recognition modules in order to detect the most subtle sounds, but not every fault sound requires the highest-resolution module to detect it. If low-resolution modules are uniformly used, the detection effect will be poor. Therefore, it is necessary to design a practical and autonomous learning spatial equipment group operation status monitoring system. Summary of the invention

[0004] The purpose of the present invention is to provide a spatial equipment group operation status monitoring system with autonomous learning to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above-mentioned technical problems, the present invention provides the following technical solutions: a spatial equipment group operation status monitoring system with autonomous learning, including a sound condition analysis module and a temperature condition analysis module. The sound condition analysis module is used to judge the operation status of the equipment according to the operation sound of the equipment, and the temperature condition analysis module is used to judge the operation status of the equipment according to the temperature of the equipment operation environment.

[0006] According to the above technical solution, the sound condition analysis module includes a signal acquisition module, a feature extraction module, a sound feature library, a fault detection module, an autonomous learning module, and a sound analysis module. The feature extraction module and the fault detection module are electrically connected to the sound feature library, the signal acquisition module is electrically connected to the fault location module, the autonomous learning module is electrically connected to the sound feature library and the fault detection module, and the sound analysis module is electrically connected to the fault detection module;

[0007] The signal acquisition module is used to collect sound signals when the equipment is running, the feature extraction module is used to extract specific types of sounds from the sound signals, the sound type library is used to store the sounds of various fault operating conditions, the fault detection module is used to match the sound signals with the sound signals in the sound feature library, the autonomous learning module is used to record the current sound into the sound feature library when an unknown equipment operating failure occurs, and the sound analysis module is used to analyze the sound and determine its characteristics.

[0008] According to the above technical solution, the working steps of the detection system are:

[0009] S1. After turning on the machine, start the signal acquisition module to collect the sound signal of the equipment operation;

[0010] S2. Compare the collected sound with the sound in the sound feature library. If the sound matches the sound of the device operation failure, determine that the current device operation failure;

[0011] S3. If the fault detection module detects that the sound has changed, but it is not the fault sound in the sound feature library, and it is manually detected that the current device does have an operating fault, the autonomous learning module stores the changed sound into the sound feature library;

[0012] S4. If the fault detection module fails to detect the fault change, and it is manually detected that the current device does have an operating fault, the sound analysis module is started to change the resolution of the current device operating sound to make it clearer until the fault can be detected.

[0013] According to the above technical solution, the sound analysis module is divided into a high-resolution unit, a low-resolution unit, a resolution allocation module, and a wireless transmission module. The resolution allocation module and the wireless transmission module are both electrically connected to the high-resolution unit and the low-resolution unit, and the wireless transmission module is electrically connected to the signal acquisition module.

[0014] The high-resolution unit is used to analyze subtle device operation sound signals, the low-resolution unit is used to routinely detect the operation status of the current device, the wireless transmission module is used to transmit the sound signals between various signal acquisition modules, and the resolution allocation module is used to allocate the resolution of each detection point.

[0015] According to the above technical solution, in the above step S4, the working process of the sound analysis module is:

[0016] S4-1, when the sound is analyzed normally, each detection point starts the low-resolution unit to work normally, and the high-resolution unit is in a non-working state;

[0017] S4-2, at regular intervals, the high-resolution units at each monitoring point start working in turn to conduct spot checks on the current status of the equipment to identify potential safety hazards of the current equipment. During the spot check, the sound signal of the point is transmitted to the high-resolution units at other detection points through the wireless transmission module for analysis;

[0018] S4-3. When it is manually detected that the current equipment does have an operating fault and the fault cannot be identified with the current resolution, the proportion of the high-resolution unit of the detection point taking over the tasks of other detection points is reduced, and the sound signal is transmitted to other detection points for collaborative analysis.

[0019] According to the above technical solution, in the above step S4-3, the method for the high-resolution unit of a certain detection point to undertake the allocation of other detection points is that when the equipment failure is manually detected, the timing is started and the resolution of the high-resolution unit of the detection position is gradually increased until the highest resolution is reached or a sound match with the sound feature library is detected, which is specifically as follows:

[0020]

[0021] Where P is the proportion of the sound analysis module of the current detection point processing the image tasks of other detection points in real time, P0 is the overall resolution, P1 is the resolution occupied by the low-resolution unit processing the resolution task, t0 is the time to trigger the high-resolution unit to fully work, and t1 is the duration of the equipment failure until it is manually detected.

[0022] According to the above technical solution, the temperature condition analysis module includes an infrared sensing unit, a human body contour fitting unit, and a human body posture determination unit, the human body posture determination unit is electrically connected to the fault detection module, and the human body posture determination unit is electrically connected to the resolution allocation module;

[0023] The infrared sensing unit is used to detect the body of the staff member by infrared sensing, the human body contour fitting unit is used to fit the human body image sensed by infrared, and the human body posture determination unit is used to determine the current detection posture of the staff member.

[0024] According to the above technical solution, in the above step S3, the method for manually detecting equipment failure is:

[0025] When the inspector finds a fault in the equipment and conducts manual inspection, the infrared sensing unit is started to scan the human body contour, and the human body posture determination unit is used to determine the current posture position and whether the equipment operation is being observed. If it is found that observation is in progress, the resolution of the high-resolution unit near the current human body position is increased.

[0026] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention can judge the type of fault occurring in the current operation of the equipment according to the sound of the equipment operation, replacing manual identification, and can adjust the resolution of the current equipment sound according to whether a fault is detected, using low resolution for sounds that can be directly detected and high resolution for faults that are more difficult to detect, thereby further saving the cost of the sound sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0028] Figure 1 It is a schematic diagram of the overall principle of the present invention; DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] See also Figure 1 , the present invention provides a technical solution: a spatial equipment group operation status monitoring system with autonomous learning, including a sound status analysis module and a temperature status analysis module, the sound status analysis module is used to judge the operation status of the equipment according to the operation sound of the equipment, and the temperature status analysis module is used to judge the operation status of the equipment according to the temperature of the equipment operation environment;

[0031] The sound condition analysis module includes a signal acquisition module, a feature extraction module, a sound feature library, a fault detection module, an autonomous learning module, and a sound analysis module. The feature extraction module and the fault detection module are electrically connected to the sound feature library, the signal acquisition module is electrically connected to the fault location module, the autonomous learning module is electrically connected to the sound feature library and the fault detection module, and the sound analysis module is electrically connected to the fault detection module;

[0032] The signal acquisition module is used to collect the sound signals when the equipment is running, the feature extraction module is used to extract specific types of sounds from the sound signals, the sound type library is used to store the sounds of various fault operating conditions, the fault detection module is used to match the sound signals with the sound signals in the sound feature library, the autonomous learning module is used to record the current sound into the sound feature library when an unknown equipment operation fault occurs, and the sound analysis module is used to analyze the sound and identify its characteristics;

[0033] The working steps of the detection system are:

[0034] S1. After turning on the machine, start the signal acquisition module to collect the sound signal of the equipment operation;

[0035] S2. Compare the collected sound with the sound in the sound feature library. If the sound matches the sound of the device operation failure, determine that the current device operation failure;

[0036] S3. If the fault detection module detects that the sound has changed, but it is not the fault sound in the sound feature library, and it is manually detected that the current device does have an operating fault, the autonomous learning module stores the changed sound into the sound feature library;

[0037] S4. If the fault detection module fails to detect the fault change, and it is manually detected that the current device does have an operating fault, the sound analysis module is started to change the resolution of the operating sound of the current device to make it clearer until the fault can be detected;

[0038] The sound analysis module is divided into a high-resolution unit, a low-resolution unit, a resolution allocation module, and a wireless transmission module. The resolution allocation module and the wireless transmission module are both electrically connected to the high-resolution unit and the low-resolution unit, and the wireless transmission module is electrically connected to the signal acquisition module.

[0039] The high-resolution unit is used to analyze subtle equipment operation sound signals, the low-resolution unit is used to routinely detect the operation status of the current equipment, the wireless transmission module is used to transmit the sound signals between various signal acquisition modules, and the resolution allocation module is used to allocate the resolution of each detection point;

[0040] In the above step S4, the working process of the sound analysis module is as follows:

[0041] S4-1, when the sound is analyzed normally, each detection point starts the low-resolution unit to work normally, and the high-resolution unit is in a non-working state;

[0042] S4-2, at regular intervals, the high-resolution units at each monitoring point start working in turn to conduct spot checks on the current status of the equipment to identify potential safety hazards of the current equipment. During the spot check, the sound signal of the point is transmitted to the high-resolution units at other detection points through the wireless transmission module for analysis;

[0043] S4-3. When it is manually detected that the current device does have an operating fault and the fault cannot be identified with the current resolution, the proportion of the high-resolution unit of the detection point taking on tasks of other detection points is reduced, and the sound signal is transmitted to other detection points for collaborative analysis;

[0044] In the above step S4-3, the method for the high-resolution unit at a certain detection point to undertake the allocation of other detection points is that when the equipment failure is manually detected, the timing is started and the resolution of the high-resolution unit at the detection position is gradually increased until the highest resolution is reached or a sound matching with the sound feature library is detected, which is specifically as follows:

[0045]

[0046] Where P is the proportion of the sound analysis module of the current detection point processing the image tasks of other detection points in real time, P0 is the overall resolution, P1 is the resolution occupied by the low-resolution unit processing the resolution task, t0 is the time to trigger the high-resolution unit to work completely, t1 is the duration of the equipment failure detected manually. Since the longer the equipment failure lasts, it means that the current gradually increased resolution cannot detect the fault, so the fault can only be found by increasing the resolution. For ordinary problems, only low resolution is needed to find the fault, which is beneficial to energy conservation and emission reduction. At the same time, multiple high-resolution units work together. Since it is impossible for all equipment to fail at the same time, this allocation method can achieve the highest work efficiency while saving costs;

[0047] The temperature condition analysis module includes an infrared sensing unit, a human body contour fitting unit, and a human body posture determination unit, the human body posture determination unit is electrically connected to the fault detection module, and the human body posture determination unit is electrically connected to the resolution allocation module;

[0048] The infrared sensing unit is used to detect the body of the staff member by infrared sensing, the human body contour fitting unit is used to convert the human body image sensed by infrared, and the human body posture determination unit is used to determine the detection posture of the current staff member;

[0049] In the above step S3, the method of manually detecting equipment failure is:

[0050] When the inspector finds a fault in the equipment and conducts manual inspection, the infrared sensing unit is started to scan the human body contour, and the human body posture determination unit is used to determine the current posture position and whether the equipment operation is being observed. If it is found that observation is in progress, the resolution of the high-resolution unit near the current human body position is increased.

[0051] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0052] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A space equipment group operation status monitoring system with autonomous learning, characterized by: It includes a sound condition analysis module and a temperature condition analysis module. The sound condition analysis module is used to judge the operating condition of the device according to the operating sound of the device, and the temperature condition analysis module is used to judge the operating condition of the device according to the temperature of the operating environment of the device; The sound condition analysis module includes a signal acquisition module, a feature extraction module, a sound feature library, a fault detection module, an autonomous learning module, and a sound analysis module. The feature extraction module and the fault detection module are electrically connected to the sound feature library, the signal acquisition module is electrically connected to the fault location module, the autonomous learning module is electrically connected to the sound feature library and the fault detection module, and the sound analysis module is electrically connected to the fault detection module; The signal acquisition module is used to collect sound signals when the equipment is running, the feature extraction module is used to extract specific types of sounds from the sound signals, the sound feature library is used to store sounds of various fault operating conditions, the fault detection module is used to match the sound signal with the sound signal in the sound feature library, the autonomous learning module is used to record the current sound into the sound feature library when an unknown equipment operation fault occurs, and the sound analysis module is used to analyze the sound and identify its characteristics; The working steps of the monitoring system are: S1. After turning on the machine, start the signal acquisition module to collect the sound signal of the equipment operation; S2. Compare the collected sound with the sound in the sound feature library. If the sound matches the sound of the device operation failure, determine that the current device operation failure occurs. S3. If the fault detection module detects that the sound has changed, but it is not the fault sound in the sound feature library, and it is manually detected that the current device does have an operating fault, the autonomous learning module stores the changed sound into the sound feature library; S4. If the fault detection module fails to detect the fault change, and it is manually detected that the current device does have an operating fault, the sound analysis module is started to change the resolution of the operating sound of the current device to make it clearer until the fault can be detected; The sound analysis module is divided into a high-resolution unit, a low-resolution unit, a resolution allocation module, and a wireless transmission module. The resolution allocation module and the wireless transmission module are both electrically connected to the high-resolution unit and the low-resolution unit, and the wireless transmission module is electrically connected to the signal acquisition module. The high-resolution unit is used to analyze subtle device operation sound signals, the low-resolution unit is used to routinely detect the operation status of the current device, the wireless transmission module is used to transmit the sound signal between various signal acquisition modules, and the resolution allocation module is used to allocate the resolution of each detection point; In the above step S4, the working process of the sound analysis module is as follows: S4-1, when the sound is analyzed normally, each detection point starts the low-resolution unit to work normally, and the high-resolution unit is in a non-working state; S4-2, at regular intervals, the high-resolution units at each monitoring point start working in turn to conduct spot checks on the current status of the equipment to identify potential safety hazards of the current equipment. During the spot check, the sound signal of the point is transmitted to the high-resolution units at other detection points through the wireless transmission module for analysis; S4-3. When it is manually detected that the current device does have an operating fault and the fault cannot be identified with the current resolution, the proportion of the high-resolution unit of the detection point taking on tasks of other detection points is reduced, and the sound signal is transmitted to other detection points for collaborative analysis; In the above step S4-3, the method for the high-resolution unit at a certain detection point to undertake the allocation of other detection points is that when the equipment failure is manually detected, the timing is started and the resolution of the high-resolution unit at the detection position is gradually increased until the highest resolution is reached or a sound matching with the sound feature library is detected, which is specifically as follows: ; In the formula The ratio of the sound analysis module of the current detection point to the image tasks of other detection points in real time. For the overall resolution, The resolution power used by low-resolution units to process resolution tasks. To trigger the high-resolution unit to fully work, The duration of the equipment failure after manual detection; The temperature condition analysis module includes an infrared sensing unit, a human body contour fitting unit, and a human body posture determination unit, wherein the human body posture determination unit is electrically connected to the fault detection module, and the human body posture determination unit is electrically connected to the resolution allocation module; The infrared sensing unit is used to detect the body of the staff member by infrared sensing, the human body contour fitting unit is used to convert the human body image sensed by infrared, and the human body posture determination unit is used to determine the detection posture of the current staff member; In the above step S3, the method of manually detecting equipment failure is: When the inspector finds a fault in the equipment and conducts manual inspection, the infrared sensing unit is started to scan the human body contour, and the human body posture determination unit is used to determine the current posture position and whether the equipment operation is being observed. If it is found that observation is in progress, the resolution of the high-resolution unit near the current human body position is increased.

Images