CN115306718A

CN115306718A - Method, apparatus, device, medium and program product for detecting screw compressor failure

Info

Publication number: CN115306718A
Application number: CN202210833918.9A
Authority: CN
Inventors: 吴新涛
Original assignee: Petromentor International Education Beijing Co ltd
Current assignee: Petromentor International Education Beijing Co ltd
Priority date: 2022-07-15
Filing date: 2022-07-15
Publication date: 2022-11-08
Anticipated expiration: 2042-07-15
Also published as: CN115306718B

Abstract

The application discloses a method, a device, equipment, a medium and a program product for detecting faults of a screw compressor. The screw compressor fault detection method comprises the following steps: acquiring at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor; obtaining temperature information of the screw compressor in a working state based on the at least one frame of infrared temperature field image; comparing the temperature information with temperature threshold information to obtain a first comparison result; wherein the temperature threshold information is a temperature threshold of the screw compressor; the temperature threshold information is determined based on production information of the screw compressor; and determining the fault state of the screw compressor based on the first comparison result. The state of the screw compressor is detected accurately, efficiently and at low cost.

Description

Method, apparatus, device, medium and program product for detecting screw compressor failure

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, a medium, and a program product for detecting a fault in a screw compressor.

Background

The screw compressor has simple structure, few vulnerable devices, low exhaust temperature and insensitivity to a large amount of lubricating oil contained in a refrigerant, can work under the condition of larger pressure difference or pressure ratio, has good gas transmission regulation characteristic, and can be widely applied to refrigerating devices such as freezing, refrigeration, air conditioning, chemical engineering processes and the like. The application of the method in the fields of industrial production and the like is wide, so that the method is rapidly developed.

With the rapid development of the screw compressor technology, the detection of the running state of the screw compressor is more and more important, the running state of the screw compressor is usually detected manually at present, so that the detection result is inaccurate, the labor is wasted, and the detection efficiency is low.

Disclosure of Invention

An object of the embodiments of the present application is to provide a method, an apparatus, a device, a medium, and a program product for detecting a fault of a screw compressor, so as to achieve an effect of accurately, efficiently, and inexpensively detecting a state of the screw compressor.

The technical scheme of the application is as follows:

in a first aspect, a method for detecting a fault of a screw compressor is provided, the method comprising:

acquiring at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor;

obtaining temperature information of the screw compressor in a working state based on the at least one frame of infrared temperature field image;

comparing the temperature information with temperature threshold information to obtain a first comparison result; wherein the temperature threshold information is a temperature threshold of the screw compressor; the temperature threshold information is determined based on production information of the screw compressor;

and determining the fault state of the screw compressor based on the first comparison result.

In a second aspect, there is provided a screw compressor failure detection apparatus, the apparatus comprising:

the first acquisition module is used for acquiring at least one frame of infrared temperature field image acquired by the infrared imager in the working process of the screw compressor;

the first determining module is used for obtaining temperature information of the screw compressor in a working state based on the at least one frame of infrared temperature field image;

the second determining module is used for comparing the temperature information with temperature threshold information to obtain a first comparison result; wherein the temperature threshold information is a temperature threshold of the screw compressor; the temperature threshold information is determined based on production information of the screw compressor;

and the third determining module is used for determining the fault state of the screw compressor based on the first comparison result.

In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or an instruction stored in the memory and executable on the processor, where the program or the instruction, when executed by the processor, implements the steps of the method for detecting a failure of a screw compressor according to any one of the embodiments of the present application.

In a fourth aspect, the present application provides a readable storage medium, on which a program or instructions are stored, and the program or instructions, when executed by a processor, implement the steps of the screw compressor fault detection method according to any one of the embodiments of the present application.

In a fifth aspect, the present application provides a computer program product, where instructions of the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the steps of the method for detecting a fault of a screw compressor according to any one of the embodiments of the present application.

The technical scheme provided by the embodiment of the application at least has the following beneficial effects:

according to the screw compressor fault detection method provided by the embodiment of the application, based on at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor, the temperature information under the working state of the screw compressor can be obtained, then the temperature information is compared with the temperature threshold value information to obtain a first comparison result, and based on the first comparison result, the fault state of the screw compressor is determined.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application and are not to be construed as limiting the application.

Fig. 1 is a schematic structural diagram of a screw compressor fault detection system according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of a method for detecting a fault in a screw compressor according to an embodiment of the first aspect of the present application;

fig. 3 is a schematic diagram of a single-point sampling early warning process according to an embodiment of the first aspect of the present application;

fig. 4 is a schematic diagram of a two-point sampling early warning process according to an embodiment of the first aspect of the present application;

fig. 5 is a second schematic flowchart of a method for detecting a fault of a screw compressor according to an embodiment of the first aspect of the present application;

FIG. 6 is a schematic flow chart of a pedestrian post-processing procedure according to an embodiment of the first aspect of the present application;

fig. 7 is a schematic structural diagram of a screw compressor fault detection device provided in an embodiment of a second aspect of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the third aspect of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples consistent with certain aspects of the application, as detailed in the appended claims.

Before the technical solution of the present application is introduced, a background of the technical solution of the present application is first introduced:

a screw compressor has a pair of intermeshing helical male and female rotors in a cylinder, both rotors having a plurality of concave teeth which rotate in opposite directions. The clearance between the rotors and between the casing and the rotors is only 5-10 filaments, the main rotor (also called male rotor or male rotor) is driven by an engine or a motor (mostly driven by the motor), and the other rotor (also called female rotor or female rotor) is driven by an oil film formed by oil injection of the main rotor or driven by synchronous gears at the ends of the main rotor and the female rotor. There is theoretically no metal contact in the drive.

The length and the diameter of the rotor determine the displacement (flow) and the exhaust pressure of the compressor, and the longer the rotor is, the higher the pressure is; the larger the rotor diameter, the greater the flow.

The spiral rotor groove is full of air when passing through the air suction port, when the rotor rotates, the rotor groove is sealed by the shell wall to form a compression chamber, and after the rotor groove is sealed, lubricating oil is sprayed into the compression chamber to play roles in sealing, cooling and lubricating. When the rotor rotates to compress the lubricant and gas (oil-gas mixture for short), the volume of the compression chamber is reduced, and the oil-gas mixture is compressed towards the exhaust port. When the compression chamber passes through the exhaust port, the oil-gas mixture is exhausted from the compressor, completing an intake-compression-exhaust process.

Each rotor of the screw machine is supported by antifriction bearings which are secured by end caps near the ends of the rotating shaft. The inlet end is supported by roller bearings and the exhaust end is supported by a bearing, typically the exhaust end, with opposing tapered rollers to locate the rotor, i.e., a thrust bearing, to resist axial thrust, to carry radial loads, and to provide the necessary minimum clearance for axial travel.

The working cycle can be divided into three processes of suction, compression and exhaust. As the rotor rotates, each pair of intermeshing teeth successively completes the same duty cycle.

The method comprises the steps of obtaining temperature information under the working state of the screw compressor based on at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor, comparing the temperature information with temperature threshold value information to obtain a first comparison result, and determining the fault state of the screw compressor based on the first comparison result.

The method for detecting a fault of a screw compressor provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.

Fig. 1 is a screw compressor fault detection system 100 for implementing a screw compressor fault detection method according to an embodiment of the present application, where the system includes a screw compressor 101, an infrared imager 106, a network video recorder 107, a communication medium 102, and a server 108.

In some embodiments of the present application, the workflow of the screw compressor fault detection system 100 may be: according to the specific size of the object to be detected (for example, a screw compressor), and in combination with the following infrared imager selection recommendation, selecting a suitable infrared thermal imager 106, and further according to the size of the screw compressor and the parameters of the infrared imager, calculating the installation position, the horizontal range R (e.g., 104 in fig. 1), and the vertical height H (e.g., 105 in fig. 1) of the screw compressor to the infrared thermal imager. The infrared thermal imager will gather infrared temperature field information (specifically can be infrared temperature field video, because infrared imager can continuously monitor screw compressor always), pass to network camera 107 through communication medium 102, network camera 107 stores infrared temperature field information, can send to server 108 through communication medium 102 simultaneously, utilize server 108 to carry out analysis to infrared temperature field information, report to the police, utilize the display of server 108 to realize functions such as video editing, review, download simultaneously.

It should be noted that the communication medium 102 may be any type of network or networks known in the art or developed in the future, such as simple communication cable, internet backbone, ethernet, wireless Fidelity (WIFI), worldwide Interoperability for Microwave Access (WIMAX), wireless communication, broadband over power line, coaxial cable, etc.

It should be noted that, in the actual arrangement of the distance R and the height H in fig. 1, due to the limitation of the wall or the high beam to which the on-site infrared imager 106 is attached, the installation distance H and the height R are optimally selected within the allowable range of the calculation result.

In some embodiments of the present application, the system 100 for detecting a screw compressor fault provided in the embodiments of the present application may be applied to an oil and gas field screw compressor unit, may also be applied to other motive equipment in an oil and gas field, such as various centrifugal pumps, reciprocating compressors, and the like, and may also be applied to other industrial motive equipment.

In some embodiments of the present application, different capabilities and functions of the infrared imager, such as pixels, thermometry range, lenses, etc., may be tailored to different field use needs, and the following are type-selection suggestions for some typical applications:

A. for electrical equipment

The high temperature range is generally up to 200 ℃.

Low temperature ranges typically require up to-20 c, considering that some equipment may be operated outdoors.

For a typical electrical device or component, the pixels of the infrared imager are 160 × 120, and a standard lens is selected.

For long-distance and small target measurement (such as wire clamps of power transmission lines), 320 × 240 pixels or 640 × 480 pixels and higher pixels are recommended to be selected, and a telephoto lens is selected.

For close-range, large target measurements (e.g. 1 meter in 1 heat map showing the temperature distribution throughout the cabinet), it is recommended to choose a wide-angle lens.

For objects with small temperature difference (such as alternating current high-voltage electrical equipment and the like), an infrared imager with high thermal sensitivity is recommended.

If the field needs to have a long-time continuous detection requirement, an external power supply is selected.

B. Aiming at machinery and electromechanical equipment

Selecting an infrared imager with the temperature of 250 ℃, 350 ℃ and 600 ℃ according to the actual temperature.

For a general mechanical and electromechanical device, the pixels of the infrared imager are 160 × 120, and a standard lens is selected.

For partial long-distance and small target measurement (such as high-altitude pipeline detection and the like), a long-focus lens is recommended to be matched.

For partial close-range, large target measurements (e.g., range displays the overall temperature profile of the furnace), it is recommended to choose a wide-angle lens.

For testing parts of equipment needing sealing (such as measuring the internal temperature of a closed heating furnace), an infrared window assembly is recommended to be additionally arranged.

C. Aiming at research and development and quality management equipment

Selecting an infrared imaging instrument with the temperature of 250 ℃, 350 ℃, 600 ℃, 1200 ℃ and 2000 ℃ according to the actual temperature.

For general objects (e.g., chips, circuit boards, various devices, etc.), it is recommended to select the pixels of the infrared imager to be 320 × 240 or 640 × 480 pixels and higher, and to select a standard lens.

For partial distance measurements, it is recommended to choose a telephoto lens.

For small target measurements (e.g., micro-chip temperature distribution within 1mm x 1 mm), it is recommended to choose a macro lens.

For targets partially within the sealed enclosure (e.g., to sense device temperature inside the heater), it is advisable to add an infrared window assembly.

For continuous measurement in some fields, an infrared imager with an external power supply or a video output function is recommended to be selected, and a thermal imager with a continuous shooting function can be selected in some fields.

In some embodiments of the present application, when the infrared imager is mounted at an object to be detected (e.g., a screw compressor), the mounting position of the infrared imager has the following reference parameters:

the first parameter is as follows: the detection distance of the infrared imager = the measured object size ÷ IFOV, so the smaller the spatial resolution (IFOV), the farther away it can be measured.

For example: the wire clamp size of the transmission line is generally 50mm, and if a FlukeTi25 thermal imager is used, the IFOV is 2.5mRad, and the maximum detection distance is 50/2.5 =20m.

And a second parameter: the minimum detection target size = IFOV × minimum focus distance, so the smaller the IFOV, the smaller the minimum focus distance, the smaller the target can be detected.

In some embodiments of the present application, the object to be monitored may be a screw compressor of a gas production plant of a certain oil and gas field, and the selected imager may be a FlukeTi25 thermal imager; spatial resolution (IFOV): 2.6mRad; pixel: 320 is multiplied by 240; minimum focusing distance: 0.5m; minimum detection size: 1; spatial resolution (IFOV): 2.5mRad; pixel: 160 x 120; minimum focusing distance: 0.15m.3mm; minimum detection size: 0.38mm.

In some embodiments of the present application, the following issues may be noted when installing an infrared imager:

should install the equipment of installing (infrared imager) and switch on the inspection, add the inspection of electricity one by one to infrared imager promptly before the installation to carry out the coarse adjustment, just can install when infrared imager normal operation, the installation aperture and the position of inspection camera (infrared imager) and support, cloud platform pay attention to should not open camera lens lid in the camera process of moving and erectting. The intelligent infrared imager is arranged near a monitoring target (a screw compressor) and is not easy to be damaged and shielded by the outside, and the installation position does not influence the work of field equipment and the normal activities of personnel. The camera lens should aim at a monitoring target from a light source direction, and backlight installation should be avoided, otherwise image blurring or halation is easily caused; when backlighting is necessary, the contrast in the surveillance area should be minimized.

The infrared imaging instrument is not required to be arranged near an air outlet of the air conditioner or in a place full of smoke and dust, otherwise the infrared imaging instrument is easy to condense water vapor on the lens due to the change of temperature, and the lens is polluted. The infrared imager is not aimed at the place exposed to the light source, such as spot light source like spot light, for a long time. When the infrared imager is installed, the cable exposed out of the shield is wrapped by the hose, so that a cable plug is not required to bear the dead weight of the cable. The installation of the equipment is firm and stable. The power supply, the video line and the control line are all fixed, and a room is left, so that the rotation of the infrared imager is not influenced. The cables should be marked permanently and visibly for ease of maintenance and management.

The screw compressor fault detection system provided by the embodiment of the application is provided with the infrared imager, monitors the infrared thermal image signals of the key parts of the screw compressor in real time based on the infrared imager, and grasps the distribution condition of the temperature field of the monitoring equipment and the temperature change of the key parts; and the server is used for carrying out data analysis on the acquired temperature data, automatically generating an electronic report and automatically early warning, so that the purpose of analyzing and monitoring the screw compressor for faults is achieved. The system absorbs the advantages of infrared monitoring automatic identification and automatic early warning, and considers the temperature of the surface and key parts of the screw compressor on the basis of the original vibration monitoring. The potential fault can be detected and diagnosed as early as possible in the controllable range of a factory, and the potential fault can be maintained reasonably and timely, so that safety accidents are avoided.

Next, a method for detecting a failure of a screw compressor provided in an embodiment of the present application is described, and fig. 2 is a schematic flowchart of the method for detecting a failure of a screw compressor provided in an embodiment of the present application, where an execution main body of the method for detecting a failure of a screw compressor may be the server 108 in fig. 1.

As shown in fig. 2, the method for detecting a fault of a screw compressor provided by the embodiment of the present application may include steps 210 to 240.

And step 210, acquiring at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor.

The infrared temperature field image can be an image for representing the temperature condition of the screw compressor in the working process. The image can be captured based on a video of the screw compressor during operation, which is collected by an infrared imager.

And step 220, obtaining temperature information of the screw compressor in the working state based on at least one frame of infrared temperature field image.

In some embodiments of the present application, at least one frame of infrared temperature field image may be detected based on a temperature detection algorithm, so as to obtain temperature information of the screw compressor in an operating state.

It should be noted that the above-mentioned obtaining of the temperature information of the screw compressor in the working state by using the temperature detection algorithm is only an example of the present application, and it should be understood by those skilled in the art that there are other ways to obtain the temperature information of the screw compressor in the working state based on at least one frame of the infrared temperature field image, and any way to obtain the temperature information of the screw compressor in the working state based on at least one frame of the infrared temperature field image belongs to the protection of the present application.

Step 230, comparing the temperature information with the temperature threshold information to obtain a first comparison result.

The temperature threshold information may be a temperature threshold of the screw compressor, and specifically may be a maximum temperature and a minimum temperature of the screw compressor.

The first comparison result may be a result obtained by comparing the temperature information with the temperature threshold information.

In some embodiments of the present application, the temperature threshold information may be determined based on production information of the screw compressor, i.e. the temperature threshold information may be determined based on specifications when the screw compressor is produced.

And 240, determining the fault state of the screw compressor based on the first comparison result.

In some embodiments of the present application, the temperature information may be compared with the temperature threshold information to obtain a first comparison result, and according to the comparison result, whether the screw compressor fails or not may be determined.

In some embodiments of the application, under the condition that it is certain that helical-lobe compressor has the trouble, alarm information can be generated to suggestion staff helical-lobe compressor trouble promotes user experience.

In some embodiments of the application, under the condition that it is determined that the screw compressor has a fault, a temperature report of the part corresponding to the target heating site can be generated so as to be checked by a worker, and user experience is improved.

Through the embodiment of the application, the temperature change and the temperature gradient characteristic of the screw compressor during operation are fully analyzed, and the infrared specificity and the image intelligent analysis of the screw compressor are combined, so that the real-time monitoring, the fault early warning and the load monitoring of the operation state of the screw compressor are realized.

The invention discloses an infrared image automatic fault identification method for a screw compressor, which comprises the steps of firstly, selecting a screw compressor to be detected, and acquiring a temperature image of equipment; then, acquiring a heating point, a heating point temperature and a normal phase temperature of the equipment by processing the temperature image; and finally, calculating relative temperature by combining the environmental reference temperature to judge the running condition and the fault information of the equipment. The method monitors the operation condition and the fault information of the screw compressor based on the infrared image processing technology, searches the temperature heating abnormal point by using the infrared temperature image processing technology, calculates the heating temperature, the normal temperature, the environmental temperature and the relative temperature of the abnormal point, automatically judges the operation condition and the fault information of the screw compressor equipment by a relative temperature difference judging method, and realizes the online rapid detection of the operation condition of the screw compressor.

In some embodiments of the present application, each frame of the infrared temperature field image may have at least one heating site of the screw compressor; each heating site may correspond to a component of the screw compressor (such as but not limited to a compressor inlet/outlet, bearings, seals, couplings, motors, etc.); the temperature threshold information may include first temperature threshold information and second temperature threshold information.

Wherein the first temperature threshold information may be a minimum temperature allowed by the screw compressor.

The second temperature threshold information may be a maximum temperature allowed for the screw compressor.

In some embodiments of the present application, a heat generation site generally refers to a critical temperature field indicating site of a screw compressor, such as may be a site at a compressor inlet/outlet, bearings, seals, couplings, motors, and the like.

In some embodiments of the present application, in order to accurately determine the fault state of the screw compressor, the above-mentioned determination of whether the screw compressor has a fault may include the following two ways:

(1) Preset point threshold algorithm

The preset point location threshold algorithm is to select a preset heating point, and determine whether the screw compressor fails or not by using temperature information of the selected preset heating point.

For the preset point threshold algorithm, two calculation methods can be specifically adopted as follows:

A. site calculation

Step 220 may specifically include:

obtaining temperature information of the parts corresponding to each heating site in a working state based on at least one frame of infrared temperature field image;

step 230 may specifically include:

comparing temperature information corresponding to the target heating site with temperature threshold information to obtain a first comparison result;

step 240 may specifically include:

and determining the fault of the screw compressor under the condition that the temperature information of the part corresponding to the target heating position is less than or equal to the first temperature threshold information and/or the temperature information of the part corresponding to the target heating position is greater than or equal to the second temperature threshold information.

Wherein the target heating site may be at least one of the at least one heating site.

In some embodiments of the present application, temperature information of a component corresponding to each heating site in an operating state may be obtained based on at least one frame of infrared temperature field image, and then the temperature information corresponding to the target heating site is compared with temperature threshold information, and a failure of the screw compressor is determined when it is determined that the temperature information of the component corresponding to the target heating site is less than or equal to first temperature threshold information and/or the temperature information of the component corresponding to the target heating site is greater than or equal to second temperature threshold information.

In one example, referring to fig. 3, if the first temperature threshold information is a and the second temperature threshold information is b, obtaining temperature information I at a heating point a, and if it is determined that I is less than or equal to a and/or I is greater than or equal to b, determining that the screw compressor has a fault, sending an early warning, and then generating a temperature report at a component corresponding to the heating point.

In the embodiment of the application, temperature information of the part corresponding to each heating site in the working state is obtained based on at least one frame of infrared temperature field image, the temperature information corresponding to the target heating site is compared with temperature threshold information to obtain a first comparison result, and when the temperature information of the part corresponding to the target heating site is determined to be smaller than or equal to the first temperature threshold information and/or the temperature information of the part corresponding to the target heating site is determined to be larger than or equal to the second temperature threshold information, the fault of the screw compressor is determined, so that whether the screw compressor is in fault or not can be accurately determined, and the fault detection accuracy of the screw compressor is improved.

B. Calculation of absolute value

In some embodiments of the present application, the target heating site may include a first target heating site and a second target heating site.

Wherein the first target heating site may be one of the at least one heating site, and the second target heating site may be another heating site of the at least one heating site other than the first target heating site.

Step 230 may specifically include:

determining an absolute value of a difference value between temperature information corresponding to the first target heating site and temperature information corresponding to the second target heating site;

comparing the absolute value with temperature threshold information to obtain a first comparison result;

step 240 may specifically include:

determining a screw compressor failure in case the absolute value is determined to be less than or equal to the first temperature threshold information, and/or the absolute value is determined to be greater than or equal to the second temperature threshold information.

In some embodiments of the present application, after obtaining temperature information of a component corresponding to a first target heating site and a second target heating site in a working state based on at least one frame of infrared temperature field image, an absolute value of a difference between the temperature information corresponding to the first target heating site and the temperature information corresponding to the second target heating site may be calculated, and if the absolute value is less than or equal to a first temperature threshold information, and/or if the absolute value is greater than or equal to a second temperature threshold information, a failure of the screw compressor is determined.

In one example, referring to fig. 4, if the first temperature threshold information is a and the second temperature threshold information is B, obtaining temperature information I at a heating point a (a first target heating point) and temperature information II at a heating point B (a second target heating point), calculating an absolute value of I-II, determining that the screw compressor has a fault if the absolute value is less than or equal to a and/or the absolute value is greater than or equal to B, sending an early warning, and then generating a temperature report at the corresponding component at the heating point a and the heating point B.

In the embodiment of the application, the absolute value of the difference value between the temperature information corresponding to the first target heating site and the temperature information corresponding to the second target heating site is determined, the absolute value is compared with the temperature threshold information to obtain a first comparison result, and the fault of the screw compressor is determined under the condition that the absolute value is smaller than or equal to the first temperature threshold information and/or the absolute value is larger than or equal to the second temperature threshold information, so that whether the screw compressor is in fault or not can be accurately determined, and the fault detection accuracy of the screw compressor is improved.

(2) Regional big data algorithm

In practical engineering applications, a single point location estimate is inaccurate. Furthermore, as the useful life of the machine increases, the factory threshold (i.e., temperature threshold information) may not be appropriate relative to the current time, and thus, blindly believing the product threshold information (i.e., temperature threshold information) is also not trustworthy. Based on the two problems, the regional big data algorithm is improved. The regional big data algorithm takes a preset heating point as a center, a certain distance as a radius, and the state of a key device of the screw compressor is detected by comparing the previous single preselected heating point or a plurality of preselected heating points, and the region can well represent the key device. Therefore, the screw compressor status is monitored using an infrared temperature field picture and the average temperature of this area is used to scale the device. And aiming at the second problem (the threshold value is not credible), the regional big data algorithm adopts a comparison idea, compares the currently acquired infrared temperature field image with the historical monitoring result stored in the database, specifically shows that the data comparison is carried out on the currently acquired infrared temperature field image and the historical monitoring result stored in the database, if the temperature curve changes of the currently acquired infrared temperature field image and the historical monitoring result are close and the temperature of the currently acquired infrared temperature field image and the historical monitoring result is basically consistent, the currently acquired infrared temperature field image can be considered to be required to be alarmed, otherwise, the alarm is not carried out.

Specific steps 220 may include:

determining first average temperature information within a preset range of a preset site based on at least one frame of infrared temperature field image;

step 230 may specifically include:

subtracting the first average temperature information from the temperature threshold information to obtain a difference value;

step 240 may specifically include:

and determining the fault of the screw compressor under the condition that the difference value is larger than the preset threshold value.

Wherein, the preset site can be any one of the at least one heating site.

The preset range may be a preset range, and may be, for example, a range centered on the preset point and having a radius of 0.5 m.

The first average temperature information may be average temperature information within a preset range of a preset location.

In the embodiment of the application, the first average temperature information in the preset range of the preset position point is determined based on at least one frame of infrared temperature field image, the first average temperature information is subtracted from the temperature threshold value information to obtain a difference value, and the fault of the screw compressor is determined under the condition that the difference value is greater than the preset threshold value, so that whether the screw compressor is in fault or not can be accurately determined, and the fault detection accuracy of the screw compressor is improved.

In some embodiments of the present application, there are some problems in determining the temperature of the screw compressor by using the infrared imager, for example, if a pedestrian intrudes into the scene and the screw compressor is just shielded, the infrared thermal field image at this time is significantly different from the infrared thermal field image when the pedestrian is not shielded, and in this case, the working state of the screw compressor cannot be reasonably estimated. It is worth mentioning that the infrared imager provides not only an infrared temperature field image but also a visible light image. Based on this, the detection of a pedestrian can be performed using a visible light image to distinguish two different situations. The specific implementation mode is as follows:

in some embodiments of the present application, after step 210, to avoid an influence of a pedestrian on a detection result, the method for detecting a fault of a screw compressor may further include:

acquiring at least one frame of visible light image acquired by an infrared imager in the working process of the screw compressor;

detecting at least one frame of visible light image to obtain a detection result of the at least one frame of visible light image;

step 220 may specifically include:

and obtaining temperature information of the screw compressor in the working state based on the infrared temperature field image corresponding to the visible light image without the pedestrian.

The visible light images can be common shot images, each frame of visible light image has a corresponding frame of infrared temperature field image, and the visible light images and the infrared temperature field images are in one-to-one correspondence.

The detection result may be used to indicate whether there is a pedestrian in at least one frame of visible light image.

In some embodiments of the present application, referring to fig. 5, after the visible light image is acquired, pedestrian detection may be performed on the visible light image, and if no pedestrian is detected, the above steps 220 to 240 are performed based on the infrared temperature field image corresponding to the visible light image. If a pedestrian is detected, the subsequent post-processing of the pedestrian and the image analysis comparison are performed (the details of the embodiment will be described later).

In the embodiment of the application, at least one frame of visible light image in the working process of the screw compressor collected by the infrared imager is obtained, the at least one frame of visible light image is detected, the detection result of the at least one frame of visible light image is obtained, the temperature information of the screw compressor in the working state is obtained based on the infrared temperature field image corresponding to the visible light image without the pedestrian, so that the pedestrian detection can be carried out based on the visible light image corresponding to the infrared temperature field image, whether the pedestrian breaks into the screw compressor or not can be accurately determined, the pedestrian is prevented from breaking into the screw compressor, and the fault detection of the screw compressor is influenced.

In some embodiments of the present application, in order to improve accuracy and efficiency of fault detection of the screw compressor, the detecting at least one frame of the visible light image to obtain a detection result of the at least one frame of the visible light image may specifically include:

inputting at least one frame of visible light image into a pre-trained pedestrian detection model to obtain a first detection result of at least one frame of visible light image;

and/or;

inputting at least one frame of visible light image into a pre-trained pedestrian segmentation detection model to obtain a second detection result of at least one frame of visible light image;

the pedestrian detection model may be a pre-trained deep learning-based neural network model, and the model may be used for detecting whether a pedestrian is in the visible light image.

The first detection result may be a detection result based on a pedestrian detection model. The first detection result may specifically include: and indicating information for indicating whether at least one frame of visible light image has a pedestrian. Specifically, the pedestrian in the visible light image may be framed by a frame.

The second detection result may be a detection result based on a pedestrian segmentation detection model. The second detection result may specifically include: the indication information for indicating whether the visible light image has the pedestrian or not and the contour information of the pedestrian can be specifically to identify the contour of the pedestrian.

In some embodiments of the present application, the pedestrian segmentation detection model may be a neural network model constructed based on a Yolov5 algorithm, yolov5 is used as a representative algorithm of a single-stage target detection algorithm, and while maintaining an extremely fast inference speed, the detection accuracy is not inferior to that of a double-stage detection algorithm. The Yolov5 algorithm idea is that pictures are sent to a backbone network, feature graphs of different scales are obtained after passing through a feature pyramid, and then classification and regression tasks are simultaneously carried out through a detection head. The label matching strategy is to grid the picture, and the cell where the center of the bounding box is located is responsible for predicting the corresponding real label. YOLOV5 uses the form of convolutional neural network (FPN) and Path Aggregation Network (PAN) in the neck network part by designing the specific backbone network structure, and uses powerful mosaic data enhancement and Mixup data enhancement, and finally obtains higher precision on the data set. Based on the created data set, the algorithm uses Yolov5 for sufficient training and learning, and finally can detect whether the picture contains a pedestrian (specifically, whether the picture contains a pedestrian or not can be a result of informing whether the pedestrian exists or not, and then the pedestrian is framed by a mark frame).

In some embodiments of the present application, referring to fig. 6, if the detection result is required to be not very accurate (i.e., it is not necessary to acquire the position information of the pedestrian accurately, i.e., it is not necessary to acquire the fine contour of the pedestrian), the above-described pedestrian detection model may be employed. If the detection result is required to be fine, a pedestrian segmentation detection model (specifically, a model constructed by using a Cascade Mask R-CNN algorithm can be adopted, and the embodiment of the application is not limited to the Cascade Mask R-CNN algorithm, and any other modes capable of obtaining the pedestrian outline belong to the protection list of the application) can be adopted, so that the accurate outline information of the pedestrian can be obtained based on the model, and the accuracy of pedestrian detection is improved.

In the embodiment of the application, a first detection result of at least one frame of visible light image is obtained by inputting at least one frame of visible light image into a pre-trained pedestrian detection model; and/or; the at least one frame of visible light image is input into the pre-trained pedestrian segmentation detection model to obtain a second detection result of the at least one frame of visible light image, so that the corresponding detection model can be selected according to the user requirement to obtain the detection result of the visible light image, and the user experience is improved.

In some embodiments of the present application, in order to further accurately detect a fault of the screw compressor, after the detecting at least one frame of the visible light image and obtaining a detection result of the at least one frame of the visible light image, the above-mentioned method for detecting a fault of the screw compressor may further include:

removing the pedestrians in the infrared temperature field image corresponding to the visible light image with the pedestrians to obtain a target infrared temperature field image;

determining second average temperature information of the target area based on the target infrared temperature field image;

comparing the second average temperature information with historical average temperature information to obtain a second comparison result;

and determining the fault state of the screw compressor based on the second comparison result.

The target infrared temperature field image can be an infrared temperature field image obtained by removing pedestrians in the infrared temperature field image.

The target area can be other areas except the area where the pedestrian is located in the target infrared temperature field image.

The historical average temperature information can be temperature information obtained by stored infrared temperature field images without pedestrians under the failure state of the screw compressor and temperature information obtained by the infrared temperature field images without pedestrians under the non-failure state of the screw compressor; namely, the historical average temperature information can be historical temperature information obtained by infrared temperature field images without pedestrians in the failure state and the non-failure state of the screw compressor. The second average temperature information may be average temperature information of a target region in the target infrared temperature field image.

The second comparison result may be a comparison result of the second average temperature information and the historical average temperature information.

In the embodiment of the application, when it is determined that the visible light image has pedestrians, the pedestrians in the infrared temperature field image corresponding to the visible light image having the pedestrians can be removed to obtain a target infrared temperature field image (namely, a pedestrian post-processing process), then second average temperature information of a target area in the target infrared temperature field image is determined, the second average temperature information is compared with historical average temperature information to obtain a second comparison result (an image analysis comparison process), and based on the second comparison result, the fault state of the screw compressor can be accurately determined, so that the accuracy of fault detection of the screw compressor is improved.

In the embodiment of the application, the temperature of the screw compressor during operation is monitored on line by using an infrared image recognition technology, and load monitoring and fault early warning are realized according to the temperature change characteristics. The infrared temperature field image is combined with the visible light image to realize comprehensive monitoring and analysis.

In the embodiment of the application, from the perspective of arranging infrared imaging monitoring, an infrared monitoring technology can be further adopted to monitor a plurality of compressors in the same plant area in real time. The infrared monitoring technology can directly indicate the focus of equipment failure, the temperature measurement is continuous and comprehensive, and the result is visualized. The intelligent identification of the temperature gradient image can predict the equipment fault through dynamic temperature difference and normal state comparison. An infrared monitoring system is arranged for a plurality of compressors, and difference infrared monitoring capable of being compared is achieved. Through comparison of multiple devices in the same factory, the universal screw compressor infrared diagnosis system is developed. A plurality of infrared cameras can share the same independent video analysis server in the embodiment of the application, the infrared monitoring fault technology does not use precedent on the screw compressor, and compared with other fault online monitoring schemes, the application is more flexible to implement and has no interference to equipment.

In the embodiment of this application, this application is more comprehensive to personnel's discernment, and the product on the market is mostly to personnel's facial feature information's discernment at present, and this application combines the special personnel of petrochemical trade on this basis, draws tens of thousands of personnel's feature information, for example wear special personnel feature information such as protective clothing, safety helmet, respirator and all cover including. More accurate discharge of human interference.

In the embodiment of the application, the temperature report of the key position of the equipment is generated by utilizing the temperature field data of the equipment, the data can be checked in real time, the data storage time can be defined according to the setting, the traceability of historical data is ensured, and the initial fault track can be inquired.

The application designs a brand-new algorithm early warning logic aiming at the problem that the pedestrian breaks into the practical engineering practice, and the warning logic of the screw compressor can be changed when the pedestrian blocks the key part of the screw compressor, so that the application judges whether the pedestrian exists in the scene by utilizing the visible light image, if the pedestrian exists, two schemes of different positioning pedestrian profiles are provided, firstly, the previous detection result (namely the detection result obtained by the pedestrian detection model) is utilized, no additional training and labeling are carried out, secondly, the more accurate pedestrian profile is pursued, and a final result is obtained by utilizing a segmentation algorithm (namely the detection model is segmented by the pedestrian). And after the corrected infrared image of the pedestrian (the infrared temperature field image after the pedestrian is removed) is obtained, monitoring the working state of the screw compressor by using a picture comparison algorithm. And if no pedestrian exists, monitoring the working state of the screw compressor by using a preselected point position threshold value method and a regional big data method. Overall, the present application has a very strong practical significance, substantially achieving the first objective.

It should be noted that, in the method for detecting a failure of a screw compressor provided in the embodiment of the present application, the execution main body may be a screw compressor failure detection apparatus, or a control module in the screw compressor failure detection apparatus for executing the method for detecting a failure of a screw compressor.

Based on the same inventive concept as the screw compressor fault detection method, the application also provides a screw compressor fault detection device. The screw compressor failure detection device provided in the embodiment of the present application is described in detail below with reference to fig. 7.

Fig. 7 is a schematic structural diagram illustrating a screw compressor failure detection apparatus according to an exemplary embodiment.

As shown in fig. 7, the screw compressor failure detection apparatus 700 may include:

the first acquisition module 710 is configured to acquire at least one frame of infrared temperature field image acquired by the infrared imager in a working process of the screw compressor;

the first determining module 720 is configured to obtain temperature information of the screw compressor in the working state based on the at least one frame of infrared temperature field image;

the second determining module 730, configured to compare the temperature information with temperature threshold information to obtain a first comparison result; wherein the temperature threshold information is a temperature threshold of the screw compressor; the temperature threshold information is determined based on production information of the screw compressor;

a third determining module 740, configured to determine a fault state of the screw compressor based on the first comparison result.

In the embodiment of the application, at least one frame of infrared temperature field image acquired by an infrared imager in the working process of the screw compressor is acquired based on a first acquisition module, temperature information under the working state of the screw compressor is acquired based on a first determination module according to the at least one frame of infrared temperature field image, the temperature information is compared with temperature threshold value information based on a second determination module to obtain a first comparison result, and the fault state of the screw compressor is determined based on a third determination module according to the first comparison result.

In some embodiments of the present application, each of the infrared temperature field images has at least one heat generation site of the screw compressor therein; each heating point corresponds to one part of the screw compressor; the temperature threshold information includes first temperature threshold information and second temperature threshold information.

In some embodiments of the present application, in order to accurately determine the fault status of the screw compressor, the first determination module 720 may be specifically configured to: obtaining temperature information of the parts corresponding to each heating point in the working state based on the at least one frame of infrared temperature field image;

the second determining module 730 may specifically be configured to: comparing temperature information corresponding to the target heating site with temperature threshold information to obtain a first comparison result; wherein the target fever site is at least one of the at least one fever site;

the third determining module 740 may specifically be configured to: and determining the screw compressor to be in fault under the condition that the temperature information of the parts corresponding to the target heating position is smaller than or equal to first temperature threshold information and/or the temperature information of the parts corresponding to the target heating position is larger than or equal to second temperature threshold information.

In some embodiments of the present application, the target heating site comprises a first target heating site and a second target heating site; in order to further improve the accuracy of the fault detection of the screw compressor, the second determining module 730 may be specifically configured to: determining an absolute value of a difference value between the temperature information corresponding to the first target heating site and the temperature information corresponding to the second target heating site; comparing the absolute value with temperature threshold information to obtain a first comparison result;

the third determining module 740 may specifically be configured to: determining that the screw compressor is faulty if the absolute value is determined to be less than or equal to the first temperature threshold information and/or the absolute value is determined to be greater than or equal to the second temperature threshold information.

In some embodiments of the present application, to further improve the accuracy of fault detection of the screw compressor, the first determination module 720 may be specifically configured to: determining first average temperature information within a preset range of a preset site based on the at least one frame of infrared temperature field image; wherein the preset site is any one of the at least one heating site;

the second determining module 730 may specifically be configured to: subtracting the first average temperature information from the temperature threshold information to obtain a difference value;

the third determining module 740 may specifically be configured to: determining that the screw compressor is faulty if it is determined that the difference is greater than a preset threshold.

In some embodiments of the present application, in order to avoid the influence of a pedestrian on the detection result, the screw compressor failure detection apparatus mentioned above may further include:

the second acquisition module is used for acquiring at least one frame of visible light image acquired by the infrared imager in the working process of the screw compressor; each frame of visible light image has a corresponding frame of infrared temperature field image;

a fourth determining module, configured to detect the at least one frame of visible light image to obtain a detection result of the at least one frame of visible light image; the detection result is used for indicating whether a pedestrian exists in the at least one frame of visible light image;

the first determining module 720 may specifically be configured to: and obtaining the temperature information of the screw compressor in the working state based on the infrared temperature field image corresponding to the visible light image without the pedestrian.

In some embodiments of the present application, in order to improve the accuracy and efficiency of fault detection of the screw compressor, the fourth determination module may be specifically configured to:

inputting the at least one frame of visible light image into a pre-trained pedestrian detection model to obtain a first detection result of the at least one frame of visible light image; wherein the first detection result comprises: indicating information for indicating whether the at least one frame of visible light image has a pedestrian;

and/or;

inputting the at least one frame of visible light image into a pre-trained pedestrian segmentation detection model to obtain a second detection result of the at least one frame of visible light image; wherein the second detection result comprises: indication information for indicating whether the at least one frame of visible light image has a pedestrian or not, and contour information of the pedestrian.

In some embodiments of the present application, in order to further accurately detect a fault of the screw compressor, the above-mentioned fault detection apparatus for a screw compressor may further include:

the fifth determining module is used for eliminating the pedestrians in the infrared temperature field image corresponding to the visible light image with the pedestrians to obtain a target infrared temperature field image;

a sixth determining module, configured to determine second average temperature information of the target area based on the target infrared temperature field image; the target area is other areas except the area where the pedestrian is located in the target infrared temperature field image;

a seventh determining module, configured to compare the second average temperature information with historical average temperature information to obtain a second comparison result; the historical average temperature information is temperature information obtained by stored infrared temperature field images without pedestrians in the failure state of the screw compressor and temperature information obtained by the infrared temperature field images without pedestrians in the non-failure state of the screw compressor;

and the eighth determining module is used for determining the fault state of the screw compressor based on the second comparison result.

The device for detecting the fault of the screw compressor provided by the embodiment of the application can be used for executing the method for detecting the fault of the screw compressor provided by the embodiments of the method, the implementation principle and the technical effect are similar, and for the sake of brief introduction, the details are not repeated here.

Based on the same inventive concept, the embodiment of the application also provides the electronic equipment.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 8, the electronic device may include a processor 801 and a memory 802 that stores computer programs or instructions.

Specifically, the processor 801 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.

Memory 802 may include mass storage for data or instructions. By way of example, and not limitation, memory 802 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, a tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 802 may include removable or non-removable (or fixed) media, where appropriate. The memory 802 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 802 is non-volatile solid-state memory. The Memory may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described for the screw compressor fault detection methods provided by the above embodiments.

The processor 801 reads and executes computer program instructions stored in the memory 802 to implement any of the screw compressor failure detection methods in the above embodiments.

In one example, the electronic device can also include a communication interface 803 and a bus 810. As shown in fig. 8, the processor 801, the memory 802, and the communication interface 803 are connected via a bus 810 to complete communication therebetween.

The communication interface 803 is mainly used for implementing communication between modules, devices, units and/or devices in the embodiments of the present invention.

The bus 810 includes hardware, software, or both to couple the components of the electronic device to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 810 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.

The electronic device can execute the method for detecting the fault of the screw compressor in the embodiment of the invention, so as to realize the method for detecting the fault of the screw compressor described in fig. 2.

In addition, in combination with the method for detecting a fault of a screw compressor in the above embodiments, the embodiments of the present invention can be implemented by providing a readable storage medium. The readable storage medium having stored thereon program instructions; the program instructions, when executed by a processor, implement any of the screw compressor fault detection methods of the above embodiments.

In addition, in combination with the method for detecting a fault of a screw compressor in the above embodiments, embodiments of the present invention may be implemented by providing a computer program product. The instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform any of the screw compressor fault detection methods of the above embodiments.

It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps, after comprehending the spirit of the present invention.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed at the same time.

Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based computer instructions which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims

1. A method of screw compressor fault detection, the method comprising:

2. The method of claim 1, wherein each of said infrared temperature field images has at least one heat generation site of said screw compressor therein; each heating point corresponds to one part of the screw compressor; the temperature threshold information comprises first temperature threshold information and second temperature threshold information;

the obtaining of the temperature information of the screw compressor in the working state based on the at least one frame of infrared temperature field image comprises:

obtaining temperature information of the parts corresponding to each heating site in the working state based on the at least one frame of infrared temperature field image;

comparing the temperature information with temperature threshold information to obtain a first comparison result, including:

comparing temperature information corresponding to the target heating site with temperature threshold information to obtain a first comparison result; wherein the target heating site is at least one of the at least one heating site;

the determining the fault state of the screw compressor based on the first comparison result includes:

and determining the screw compressor to be in fault under the condition that the temperature information of the parts corresponding to the target heating position is smaller than or equal to first temperature threshold information and/or the temperature information of the parts corresponding to the target heating position is larger than or equal to second temperature threshold information.

3. The method of claim 2, wherein the target heating sites comprise a first target heating site and a second target heating site;

the comparing the temperature information corresponding to the target heating site with the temperature threshold information to obtain a first comparison result includes:

determining an absolute value of a difference value between the temperature information corresponding to the first target heating site and the temperature information corresponding to the second target heating site;

the determining the fault state of the screw compressor based on the first comparison result comprises:

determining that the screw compressor is malfunctioning if it is determined that the absolute value is less than or equal to the first temperature threshold information, and/or the absolute value is greater than or equal to the second temperature threshold information.

4. The method according to claim 2, wherein the obtaining temperature information of the screw compressor in an operating state based on the at least one frame of infrared temperature field image comprises:

determining first average temperature information within a preset range of a preset site based on the at least one frame of infrared temperature field image; wherein the preset site is any one of the at least one heating site;

determining that the screw compressor is faulty if it is determined that the difference is greater than a preset threshold.

5. The method of claim 1, wherein after said acquiring at least one frame of infrared temperature field image of the screw compressor during operation collected by the infrared imager, the method further comprises:

acquiring at least one frame of visible light image acquired by an infrared imager in the working process of the screw compressor; each frame of visible light image has a corresponding frame of infrared temperature field image;

detecting the at least one frame of visible light image to obtain a detection result of the at least one frame of visible light image; wherein the detection result is used for indicating whether the at least one frame of visible light image has a pedestrian;

and obtaining the temperature information of the screw compressor in the working state based on the infrared temperature field image corresponding to the visible light image without the pedestrian.

6. The method according to claim 5, wherein the detecting the at least one frame of the visible light image to obtain a detection result of the at least one frame of the visible light image comprises:

inputting the at least one frame of visible light image into a pre-trained pedestrian detection model to obtain a first detection result of the at least one frame of visible light image; wherein the first detection result comprises: indication information for indicating whether a pedestrian is in the at least one frame of visible light image;

and/or;

7. The method according to claim 5, wherein after the detecting the at least one frame of visible light image to obtain the detection result of the at least one frame of visible light image, the method further comprises:

determining second average temperature information of a target area based on the target infrared temperature field image; the target area is other areas except the area where the pedestrian is located in the target infrared temperature field image;

comparing the second average temperature information with historical average temperature information to obtain a second comparison result; the historical average temperature information is temperature information obtained by stored infrared temperature field images without pedestrians in the screw compressor failure state and temperature information obtained by the infrared temperature field images without pedestrians in the screw compressor non-failure state;

8. A screw compressor fault detection device, the device comprising:

9. An electronic device, characterized in that the electronic device comprises: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the screw compressor fault detection method of any one of claims 1-7.

10. A computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, implement the screw compressor fault detection method of any one of claims 1-7.

11. A computer program product, characterized in that instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the screw compressor fault detection method according to any one of claims 1-7.