A method, system, and equipment for online integrated rapid testing of air conditioner outdoor units.

Abstract

This invention belongs to the field of air conditioner fault diagnosis and discloses an online integrated rapid detection method, system, and equipment for air conditioner outdoor units. The detection method includes the following steps: preprocessing multiple sets of operating parameters of the air conditioner outdoor unit under test to obtain corresponding data vector sets; performing preliminary data fusion processing on the data vector sets to generate normalized parameters; comparing the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test; performing weighted average probability value fusion calculation on the normalized parameters, and judging the overall performance of the air conditioner outdoor unit under test based on the calculated value to obtain an overall evaluation result; assigning weight values ​​to the overall evaluation result and the single-parameter evaluation result respectively, and then performing final data fusion calculation to obtain the comprehensive status judgment result of the air conditioner outdoor unit under test. This invention can achieve rapid and efficient detection of air conditioner outdoor units.

Description

Technical Field

[0001] This invention belongs to the field of air conditioning fault diagnosis technology, and more specifically, relates to an online integrated rapid detection method, system and equipment for air conditioning outdoor units. Background Technology

[0002] Currently, the pass / fail inspection of air conditioner outdoor units on the testing line mainly relies on a combination of manual and machine judgment. The main indicators for judgment are the outdoor unit's power and refrigerant pressure. For example, the average data from the previous 40 air conditioners is calculated, with a certain margin, as a standard for the next batch of outdoor units. During the testing process, if the machine determines a product is unqualified, it will trigger an alarm, and then manual inspection will be conducted to determine if the product is truly faulty. In this testing process, the testing cycle for a single outdoor unit is relatively long. The testing line's outdoor unit testing process consists of seven steps: start-up, heating 1, heating 2, shutdown, cooling 1, cooling 2, and refrigerant recovery. This results in a running time of more than 300 seconds for a single outdoor unit, leading to low testing efficiency.

[0003] The existing testing system is a rotary line. To simultaneously meet the 8-second cycle time of the production line and the minimum testing time of 300 seconds per outdoor unit, the testing line typically has around 40 testing stations, with multiple outdoor units being tested in parallel to match the production cycle. However, this testing method occupies a relatively large space. In summary, the existing air conditioner outdoor unit testing technology has inherent drawbacks such as long testing time, low testing efficiency, and demanding testing site requirements, which do not meet the requirements of production line automation, intelligence, and high efficiency. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an online integrated rapid testing method, system and equipment for air conditioner outdoor units, so as to solve the problems of long testing time and low testing efficiency of existing air conditioner outdoor units.

[0005] To achieve the above objectives, the present invention provides an online integrated rapid testing method for air conditioner outdoor units, the testing method comprising the following steps:

[0006] S1 preprocesses the various operating parameter sets of the outdoor unit of the air conditioner under test to obtain the corresponding data vector set;

[0007] S2 performs preliminary data fusion processing on the data vector sets to generate normalized parameters;

[0008] S3 compares the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test; performs a weighted average probability value fusion calculation on the normalized parameters, and judges the overall performance of the air conditioner outdoor unit under test based on the calculated value to obtain the overall evaluation result;

[0009] S4 assigns weight values ​​to the overall evaluation result and the single-parameter evaluation result respectively, and then performs final data fusion calculation to obtain the comprehensive status judgment result of the outdoor unit of the air conditioner under test.

[0010] Furthermore, before step S1, when the outdoor unit of the air conditioner is running in a non-steady-state process, multiple types of operating parameters are collected within a certain continuous time period to obtain multiple sets of operating parameters.

[0011] Furthermore, the set of operating parameters includes at least two of the following: inlet and outlet temperatures of the outdoor unit of the air conditioner under test, S-terminal temperature, voltage, current, medium pressure, noise, and power.

[0012] Furthermore, the preliminary data fusion processing described in step S2 includes the following steps:

[0013] S21 Calculate the distance d between each pair of vectors in the data vector set. p ;

[0014] S22 based on the vector distance d p Calculate the degree of mutual support between the data vectors in the data vector set;

[0015] S23 Based on the mutual support of the data vectors, calculate the weighted average probability value of each type of operating parameter at detection time t, and use it as the normalization parameter;

[0016] S24 When new operating parameters are added at time t+1, repeat steps S21-S23.

[0017] Furthermore, in step S3, the weighted average probability values ​​of the multi-class normalized parameters are fused using the following formula:

[0018]

[0019] In the formula, i represents the number of types of operating parameter sets, j represents the probability values ​​of 0 to N mutually supporting operating parameters collected in consecutive time intervals, q represents the probability values ​​of 0 to M mutually unsupported parameters collected in consecutive time intervals, and m (air conditioning status) represents the overall evaluation result. pi This represents the normalization parameter.

[0020] Furthermore, in step S3, the step of judging the overall performance of the outdoor unit of the air conditioner under test based on the calculated value includes:

[0021] Compare the preset threshold with the calculated value:

[0022] When the calculated value is less than the preset threshold, the outdoor unit of the air conditioner under test is determined to be faulty;

[0023] When the calculated value is greater than or equal to the preset threshold, the outdoor unit of the air conditioner under test is determined to be qualified.

[0024] Furthermore, in step S4, the step of assigning weight values ​​to the overall evaluation result and the single-parameter evaluation result includes: the weight value corresponding to the overall evaluation result is greater than the weight value corresponding to each type of single-parameter evaluation result.

[0025] Furthermore, in step S4, after assigning values ​​to the overall evaluation result and the single-parameter evaluation result respectively, the final data fusion calculation is performed using the following formula:

[0026]

[0027] Where V represents the overall evaluation result after assignment, Q represents the single-parameter evaluation result after assignment, S represents the comprehensive state discrimination index of the air conditioner under test, δ1 represents the weight value assigned to the overall evaluation result of the air conditioner, and δ i The weight value assigned to the single-parameter discrimination result of class i.

[0028] According to another aspect of the present invention, an online integrated rapid testing system for air conditioner outdoor units is also provided, the testing system comprising:

[0029] The preprocessing module is used to preprocess the various operating parameter sets of the outdoor unit of the air conditioner under test to obtain the corresponding data vector set;

[0030] The first data fusion processing module is used to perform preliminary data fusion processing on the data vector sets respectively to generate normalized parameters and transmit them to the core data fusion processing module.

[0031] The second data fusion processing module is used to compare the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test; it is also used to perform weighted average probability value fusion calculation on the normalized parameters, and judge the overall performance of the air conditioner outdoor unit under test based on the calculated value to obtain the overall evaluation result.

[0032] The third data fusion processing module is used to assign weight values ​​to the overall evaluation result and the single parameter evaluation result respectively, and then perform final data fusion calculation to obtain the comprehensive status judgment result of the outdoor unit of the air conditioner under test.

[0033] According to another aspect of the invention, a computer device is also disclosed, comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the detection method as described in any of the preceding claims.

[0034] Compared with the prior art, the above technical solutions conceived by this invention have the following main advantages:

[0035] 1. The online integrated rapid detection method for air conditioner outdoor units provided by this invention adopts a three-level data fusion algorithm. First, through preliminary data fusion processing, normalized parameters are generated. Then, based on the normalized parameters, single-parameter evaluation results of the air conditioner outdoor unit under test are obtained. Simultaneously, core data fusion processing is performed on the normalized parameters, namely, weighted average probability value fusion calculation, to obtain the overall evaluation result of the air conditioner outdoor unit. Finally, the overall evaluation result and the single-parameter evaluation results are subjected to final data fusion calculation, thereby quickly obtaining the comprehensive status judgment result of the air conditioner outdoor unit under test, achieving rapid and efficient detection.

[0036] 2. The online integrated rapid detection method for air conditioner outdoor units provided by this invention can collect multiple types of air conditioner outdoor unit operating parameters, process the operating parameters through a three-level data fusion processing step, construct composite criteria using the associated calculation results, and classify the status of the product in a timely and rapid manner to establish new performance criteria for air conditioner outdoor units, replacing manual judgment steps, realizing fully automated detection, and shortening the detection time to within 80-120 seconds.

[0037] 3. The online integrated rapid detection system for air conditioner outdoor units provided by this invention realizes open, fast, and reliable online automatic detection of air conditioner outdoor units. A single detection station achieves efficient fault detection of the air conditioner outdoor unit through three-level data fusion algorithm processing. It obtains the operating status and fault points of the air conditioner outdoor unit in a short period of time during operation, and establishes new judgment criteria to replace manual judgment, thereby realizing automated detection and improving production efficiency. Furthermore, due to the shortened detection time of a single station, the detection time of this invention is shorter for the same number of detection stations. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the process of an online integrated rapid testing method for an air conditioner outdoor unit provided by the present invention;

[0039] Figure 2 This is a schematic diagram of the overall process of an online integrated rapid testing method for an air conditioner outdoor unit provided in Embodiment 1 of the present invention;

[0040] Figure 3 This is a schematic diagram of an online integrated rapid testing system for air conditioner outdoor units provided in Embodiment 2 of the present invention;

[0041] Figure 4 This is a schematic diagram of the three-level data fusion processing flow provided in the embodiments of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0043] like Figure 1 The diagram shown is a flowchart of an online integrated rapid testing method for air conditioner outdoor units provided by the present invention. The testing method includes the following steps:

[0044] S1 preprocesses the various operating parameter sets of the outdoor unit of the air conditioner under test to obtain the corresponding data vector set;

[0045] S2 performs preliminary data fusion processing on the data vector sets to generate normalized parameters;

[0046] S3 compares the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test; performs weighted average probability value fusion calculation on the normalized parameters, and judges the overall performance of the air conditioner outdoor unit under test based on the calculated value to obtain the overall evaluation result;

[0047] S4 assigns weight values ​​to the overall evaluation results and the single-parameter evaluation results respectively, and then performs the final data fusion calculation to obtain the comprehensive status discrimination index of the air conditioner outdoor unit under test. This comprehensive status discrimination index is used as the basis for judging whether the air conditioner outdoor unit under test is qualified, that is, as the comprehensive status discrimination result of the air conditioner outdoor unit.

[0048] Specifically, the preprocessing steps include: collecting operating parameters of the outdoor unit of the air conditioner during a certain continuous period of non-steady-state operation through multiple operating parameter sensors, performing analog-to-digital conversion on these operating parameters, and after accumulating a large amount of historical data (digital quantity) of the outdoor unit of the air conditioner under test, performing frequency statistics on each parameter of these historical data, that is, statistically analyzing the distribution of operating parameter values ​​along the horizontal axis in a two-dimensional coordinate system. The horizontal axis represents the change of the relevant parameter from minimum to maximum from left to right, and the vertical axis represents the frequency value of the parameter.

[0049] Then, the operating parameters of the outdoor unit of the air conditioner under test, such as voltage, current, pressure, and power, are assigned probabilistic values ​​at each acquisition time. The assignment range is [0, 1], and the assignment method is shown in formula (1):

[0050]

[0051] The historical frequency coordinates of the operating parameters are used as the regional index. Within the assignment interval [0, 1], the probability values ​​of the actual detected operating parameters of various types of air conditioner outdoor units are given from the highest frequency value to both sides. The data vector set is composed of multiple operating parameters within a certain continuous time period, thereby completing the preprocessing of the operating parameters.

[0052] More specifically, the aforementioned steps of comparing the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test are as follows: compare the current, pressure, noise, and other status parameters (such as T3 / T4 / T5 temperature) of the air conditioner outdoor unit under test with historical data or standard reference values. Each type of operating parameter has an independent judgment value. For example, the typical normal values ​​of the parameter are: current fluctuation within 15%, pressure fluctuation within 10%, noise within 60 decibels, T3 / T4 / T5 connected by default, etc. When comparing each type of operating parameter, if the performance of the air conditioner outdoor unit corresponding to the single parameter is qualified, it is assigned a value of 1; if it is unqualified, it is assigned a value of 0. The result of whether it is qualified or not is displayed in the detection system at the same time. When it is unqualified (i.e., when there is a fault), an alarm reminder is also given.

[0053] In the preferred embodiment, before step S1, since the operating parameters are processed by three-level data fusion, after the outdoor unit of the air conditioner is turned on, when the air conditioner is running in a non-steady state, multiple types of operating parameters can be collected at any time within a certain continuous period to obtain multiple sets of operating parameters. There is no need to wait for the air conditioner to run to a stable state before collecting operating parameters, which further shortens the detection time.

[0054] In a preferred embodiment, the set of operating parameters includes at least two of the following: inlet and outlet temperatures, S-terminal temperatures, voltage, current, medium pressure, noise, and power of the outdoor unit of the air conditioner under test. For example, multiple inlet temperature values ​​within a certain continuous time period are collected as one type of operating parameter set, multiple voltage values ​​within a certain continuous time period are collected as another type of operating parameter set, and multiple medium pressure values ​​within a certain continuous time period are collected as a third type of operating parameter set.

[0055] In a preferred embodiment, the preliminary data fusion processing in step S2 includes the following steps:

[0056] S21 Calculate the distance d between each pair of vectors in the data vector set. p Specifically, the calculation formula is as follows:

[0057]

[0058] Where m1 and m2 are two vectors containing the probability assignments of the air conditioner outdoor unit's operating parameters at two different times, and m1 and m2 are both scalar products, d p (m1, m2) is the distance between two vectors, and D is a 2... N ×2 N The matrix is ​​N, where N is the number of individual operating parameter data such as power and pressure collected during the unsteady-state operation of the air conditioner. The factor "1 / 2" in the formula is used to standardize the distance d. p For (m1, m2), it is guaranteed that 0 ≤ d p(m1,m2)≤1;

[0059] S22 is based on the vector distance d p Calculate the degree of mutual support among data vectors in the data vector set; specifically, determine the mutually supportive data vectors within the N sets of operating parameters, and the mutually contradictory data vectors within the N sets of operating parameters.

[0060] S23 calculates the weighted average probability value of each type of operating parameter at time t based on the degree of mutual support of data vectors, and uses it as a normalization parameter;

[0061] S24 When new operating parameters are added at time t+1, repeat steps S21-S23.

[0062] In a preferred embodiment, in step S3, the weighted average probability value fusion calculation of multiple normalized parameters is performed using the following formula:

[0063]

[0064] In the formula, i represents the number of types of operating parameter sets, j represents the probability values ​​of 0 to N mutually supporting operating parameters collected in consecutive time intervals, q represents the probability values ​​of 0 to M mutually unsupported parameters collected in consecutive time intervals, and m (air conditioning status) represents the overall evaluation result. pi This represents the normalization parameter.

[0065] In a preferred embodiment, step S3, which involves judging the overall performance of the outdoor unit of the air conditioner under test based on the calculated values, includes:

[0066] Compare the preset threshold with the calculated value: if the calculated value is less than the preset threshold, the outdoor unit of the air conditioner under test is determined to be faulty; if the calculated value is greater than or equal to the preset threshold, the outdoor unit of the air conditioner under test is determined to be qualified.

[0067] Specifically, a value of 0 is assigned when the outdoor unit of the air conditioner under test is determined to be faulty, and a value of 1 is assigned when the outdoor unit of the air conditioner under test is determined to be qualified. The result is displayed in the detection system display module, and an alarm can be issued when the air conditioner under test is unqualified.

[0068] In a preferred embodiment, step S4, which assigns weight values ​​to the overall evaluation result and the single-parameter evaluation result, includes: the weight value corresponding to the overall evaluation result is greater than the weight value corresponding to each type of single-parameter evaluation result. Specifically, the sum of the weight value corresponding to the overall evaluation result and the weight values ​​corresponding to all single-parameter evaluation results is 1.

[0069] In a further preferred embodiment, in step S4, after assigning values ​​to the overall evaluation result and the single-parameter evaluation result respectively, the final data fusion calculation is performed using the following formula:

[0070]

[0071] Where V represents the overall evaluation result after assignment, Q represents the single-parameter evaluation result after assignment, S represents the comprehensive state discrimination result of the air conditioner under test, δ1 represents the weight value assigned to the overall evaluation result of the air conditioner, and δ i The weights δ are assigned to the single-parameter discrimination results of class i; specifically, the overall evaluation result and each single-parameter evaluation result are assigned different weights δ. i (Detailed weight values ​​are determined based on empirical data).

[0072] In other embodiments, the comprehensive evaluation results data of qualified and faulty air conditioner outdoor units that have been determined are also labeled, and the labeled original data is used as training data to optimize the weighted average probability value fusion calculation rules in step S3. The purpose is to find the group characteristics of a large number of air conditioner outdoor unit samples, and on this basis, use data fusion technology to determine the status of other air conditioner outdoor units to be tested.

[0073] According to another aspect of the present invention, an online integrated rapid testing system for air conditioner outdoor units is also provided, the testing system comprising:

[0074] The preprocessing module is used to preprocess the various operating parameter sets of the outdoor unit of the air conditioner under test to obtain the corresponding data vector set;

[0075] The first data fusion processing module is used to perform preliminary data fusion processing on the data vector sets to generate normalized parameters and transmit them to the core data fusion processing module.

[0076] The second data fusion processing module is used to compare the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the air conditioner outdoor unit under test; it is also used to perform weighted average probability value fusion calculation on the normalized parameters, and judge the overall performance of the air conditioner outdoor unit under test based on the calculated value to obtain the overall evaluation result.

[0077] The third data fusion processing module is used to assign weight values ​​to the overall evaluation results and the single-parameter evaluation results respectively, and then perform the final data fusion calculation to obtain the comprehensive status judgment result of the outdoor unit of the air conditioner under test.

[0078] According to another aspect of the present invention, a computer device is also disclosed, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the detection method as described in any of the preceding embodiments.

[0079] To better illustrate the implementation details of the present invention, the following embodiments are provided to further illustrate the present invention. It should be understood that the following embodiments are only preferred implementation methods and are not intended to limit the scope of protection of the present invention in any way.

[0080] Example 1

[0081] Reference Figure 2 The specific testing process for air conditioner outdoor units is as follows: The outdoor unit is connected to the testing line from the production line. The testing system uses a scanner to scan the QR code on the unit to confirm the corresponding outdoor unit ID at each workstation. After confirmation, manual handover is performed. The entire process can be completed within 10 seconds. After the outdoor unit enters the testing line, the testing system automatically connects to the unit's media piping for a preliminary inspection of its appearance, and then initiates performance testing.

[0082] The testing time for a single outdoor unit of an air conditioner is 80s-120s, with an optimal time of 100s. During the testing, the air conditioner's operating status includes five steps: low start, heating (frequency 50Hz-70Hz), shutdown, cooling (50Hz-70Hz), and refrigerant recovery.

[0083] Reference Figure 3 Each workstation is equipped with multiple sensors for data acquisition, including medium inlet / outlet temperature sensors, voltage / current sensors, S-terminal temperature sensors, medium pressure sensors, noise sensors, and other parameters P.

[0084] refer to Figure 4 The three-level data fusion algorithm in the rapid detection solution for air conditioner outdoor units is as follows:

[0085] I. Preliminary Data Fusion Processing

[0086] Data from the outdoor unit of the air conditioner (hereinafter referred to as the outdoor unit) is collected by multiple sensors and processed by analog-to-digital conversion. After accumulating a large amount of historical data (digital data) of the outdoor unit, frequency statistics are performed on various parameters of the large amount of historical data of the outdoor unit. The distribution of parameter values ​​along the horizontal axis is statistically shown in a two-dimensional coordinate system. The horizontal axis represents the change of the relevant parameter from minimum to maximum from left to right, and the vertical axis represents the frequency value of the parameter.

[0087] Then, the operating parameters such as voltage, current, pressure, and power of each outdoor unit at each acquisition time are assigned probabilistic values. The assignment range is [0, 1]. The assignment method is as shown in the formula (1) mentioned above: that is, the historical frequency coordinate value of the parameter is the regional index. From the highest frequency value, the continuous probability values ​​of the measured operating parameters of various outdoor units are given to both sides in the assignment range [0, 1]. The detection vector m of a certain detection time is composed of the detection values ​​of multiple operating parameters at a certain time, thereby completing the preprocessing of the data.

[0088] Within a continuous detection time period, the distance between each pair of vectors in the detection vector m constructed from the probability values ​​of multiple types of operating parameters is calculated. The calculation formula is shown in the previous formula (2). After calculating the vector distance, the data of a single detection parameter is normalized to obtain the normalized parameter.

[0089] In practical applications of rapid testing of air conditioner outdoor units, the normalization parameter process can be summarized into the following 5 steps:

[0090] 1) Using N sets of data vectors of air conditioner outdoor unit operating parameters, calculate the pairwise vector distance d between each parameter. p ;

[0091] 2) Based on the vector distance d p Calculate the degree of mutual support for each data vector;

[0092] 3) Calculate the weighted average probability value m of each operating parameter at a certain detection time. pi (i is the number of types of running parameters), which is used as the normalization parameter;

[0093] 4) When new operating parameter data is added at time N+1, repeat step 1).

[0094] II. Perform core data fusion processing

[0095] Based on the previously obtained normalization parameter m pi , i = 1 to n, that is, m p1 m p2 m p3 ... m pn The weighted average probability value fusion operation is performed through the core fusion algorithm and rule 2. The calculation formula is as shown in the formula (3) above. Through calculation, the evaluation value m (air conditioning status) for the air conditioning status is obtained. This evaluation value is the evaluation value of the overall performance of the air conditioning. The specific value is in the range of [0,1].

[0096] Then, by setting a threshold of 0.5, when m (air conditioner status) is less than 0.5, the outdoor unit is judged to be in a faulty state. When m (air conditioner status) is greater than or equal to 0.5, the outdoor unit is judged to be in a qualified state. If the outdoor unit is qualified, a value of 1 is assigned; if it is unqualified, a value of 0 is assigned. The qualified or faulty result is displayed. If the outdoor unit is unqualified, an alarm is also issued, such as by sound, flashing light, or screen prompt.

[0097] While using the fusion algorithm and Rule 2 to conduct an overall evaluation of the air conditioner, single-parameter evaluations are also carried out using the current, pressure, temperature difference between the inlet and outlet of the medium, and other operating parameters analyzed by the S terminal of the outdoor unit. During specific evaluations, each type of single parameter corresponds to a reference historical data or a standard reference value. When a certain type of normalized parameter is compared with its corresponding reference historical data, it is considered qualified when the current fluctuates up and down within 15% (qualified means the performance of the outdoor unit of the air conditioner is normal), otherwise it is unqualified (unqualified means a fault); it is considered qualified when the pressure fluctuates within 10% up and down, otherwise it is unqualified; it is considered qualified when the noise is within 60 decibels, otherwise it is unqualified. For each type of performance of the outdoor unit, a value of 1 is assigned when it is qualified, and a value of 0 is assigned when it is unqualified. This result is also displayed in the system, and an alarm reminder is given when it is unqualified.

[0098] III. Finally, perform the final data fusion processing

[0099] At this stage, different weight values are assigned to the overall performance evaluation and the results of each single-parameter evaluation. In this embodiment, the weight of the overall performance evaluation δ1 = 0.5, the weight of the single pressure δ2 = 0.1, the weight of the single current δ3 = 0.1, etc., and the sum of the weights corresponding to all single-parameter evaluation results and the overall evaluation result of the outdoor unit is 1, as shown in formula (5):

[0100]

[0101] According to the different weight assignments, calculate the final fusion result, as shown in formula (6):

[0102]

[0103] For the "result" calculated from the above formula, P is the overall evaluation result of the air conditioner after assignment, Q is the single-parameter evaluation result after assignment, and S is the comprehensive judgment result of the air conditioner state.

[0104] It can be seen that in the comprehensive judgment result, the assignment of the overall evaluation result plays a dominant role, which is related to its function and the evaluation process of multi-parameter fusion; however, the "single-parameter evaluation" is also very important. While being displayed in the alarm, it will also affect the final comprehensive judgment result of the outdoor unit.

[0105] The final comprehensive judgment result value S is also a number within the range of [0, 1], and this value is the final evaluation of the air conditioner state and is displayed in the system.

[0106] After the detection is completed, the human-machine disconnection is executed, and then the outdoor unit of the air conditioner is taken offline, thus ending the entire detection step. Before executing the human-machine connection, the outdoor unit can be re-inspected.

[0107] This embodiment realizes open, fast, and reliable online automatic detection of air conditioner outdoor units. It achieves real-time fault detection of air conditioner outdoor units through three-level data fusion algorithm processing. It obtains the operating status and fault points of air conditioner outdoor units within a short period of time after they start running. At the same time, it establishes new judgment criteria to replace manual judgment, realizes automated detection, and thus improves production efficiency.

[0108] Example 2

[0109] This embodiment provides an online integrated rapid testing system for air conditioner outdoor units. The system can implement the online integrated rapid testing method for air conditioner outdoor units described in Embodiment 1. The system includes a single-station testing platform and an industrial control computer. The industrial control computer includes a memory and a processor. When the processor executes the computer program, it can implement the steps of the testing method in Embodiment 1, wherein:

[0110] The single-station testing station includes an embedded PLC module and various operating parameter acquisition modules connected to it. The operating parameter acquisition modules are used to collect the operating parameters of the air conditioner outdoor unit under test during the non-steady-state process within a certain continuous time period, and send the operating parameters to the embedded PLC module. Specifically, the operating parameter acquisition modules include: indoor unit inlet and outlet temperature sensors, voltage sensors, current sensors, outdoor unit terminal sensors, medium pressure sensors, outdoor unit noise sensors, and other types of sensors.

[0111] Embedded PLC modules are used to transmit received operating parameters to industrial control computers via industrial fieldbus;

[0112] An industrial control computer is used to receive operating parameters and use the data fusion algorithm on it to obtain the overall evaluation results and single parameter evaluation results of the air conditioner outdoor unit under test. Based on the overall evaluation results and single parameter evaluation results, it comprehensively judges whether the air conditioner outdoor unit under test is qualified (i.e. whether it is faulty or operating normally).

[0113] Specifically, industrial control computers include:

[0114] The preprocessing module is used to preprocess multiple sets of operating parameters of the outdoor unit of the air conditioner under test to obtain corresponding data vector sets. The first data fusion processing module is used to perform preliminary data fusion processing on the data vector sets to generate normalized parameters and transmit them to the core data fusion processing module. The second data fusion processing module is used to compare the magnitude of each type of normalized parameter with its corresponding standard parameter to obtain the single-parameter evaluation result of the outdoor unit of the air conditioner under test. It is also used to perform weighted average probability value fusion calculation on the normalized parameters and judge the overall performance of the outdoor unit of the air conditioner under test based on the calculated value to obtain the overall evaluation result. The third data fusion processing module is used to assign weight values ​​to the overall evaluation result and the single-parameter evaluation result respectively and then perform the final data fusion calculation to obtain the comprehensive status judgment result of the outdoor unit of the air conditioner under test.

[0115] More specifically, the industrial control computer is also equipped with a display and operating console for displaying outdoor unit evaluation results, fault alarms, and manual input of control commands; in addition, the industrial control computer also communicates with the production line plant system.

[0116] The working principle of the detection system in this embodiment is roughly as follows:

[0117] Data from the outdoor unit of the air conditioner (hereinafter referred to as the outdoor unit) is collected by multiple sensors and transmitted to an industrial control computer for analog-to-digital conversion. After accumulating a large amount of historical data (digital data) from the outdoor unit, the industrial control computer performs three-level data fusion processing according to the detection method in Example 1: First, the large amount of historical data from the outdoor unit is preprocessed as in Example 1. Then, the preprocessed data is used for preliminary data fusion to obtain normalized parameters. Next, the normalized parameters are used for core data fusion processing and single-parameter evaluation to obtain the overall evaluation result and single-parameter evaluation result of the outdoor unit. Finally, the overall evaluation result and single-parameter evaluation result are subjected to final data fusion processing to obtain a comprehensive evaluation result (i.e., whether it is faulty or operating normally).

[0118] It is understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0119] The processor may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the aforementioned prediction method can be completed by integrated logic circuits in the processor's hardware or by software instructions. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0120] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0121] For software implementation, the techniques described herein can be implemented through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processing module or external to the processing module.

[0122] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An online integrated rapid detection method for an air conditioner outdoor unit, characterized in that, The detection method comprises the following steps: S1, preprocessing a plurality of sets of operating parameters of a to-be-detected air conditioner outdoor unit to obtain a corresponding set of data vectors; S2, performing preliminary data fusion processing on the set of data vectors respectively: S21 calculates the distance between each two vectors in the data vector set d p ; S22 determining the vector distance d p calculating the mutual support degree of data vectors in the data vector set: determining mutually supported data vectors within the N sets of operating parameters, and mutually contradictory data vectors within the N sets of operating parameters; S23, calculating a weighted average probability value of each type of operating parameter at a detection time t based on the mutual support degree of the data vectors, as a normalization parameter; S24 should have a first t + 1 When new operating parameters are added at a given time, repeat steps S21-S23 to generate normalized parameters; S3, comparing the size of each normalization parameter and its corresponding standard parameter to obtain a single parameter evaluation result of the to-be-detected air conditioner outdoor unit; the normalization parameter is subjected to weighted average probability value fusion operation using the following formula: In the formula, i is the number of classes of operating parameter sets, m (A / C state) is the overall evaluation result; and judging the overall performance of the to-be-detected air conditioner outdoor unit based on the operation value to obtain an overall evaluation result; S4, assigning weight values to the overall evaluation result and the single parameter evaluation result respectively, and then performing final data fusion calculation to obtain a comprehensive state discrimination result of the to-be-detected air conditioner outdoor unit.

2. The online integrated rapid detection method for an air conditioner outdoor unit according to claim 1, characterized in that, Before step S1, when the air conditioner outdoor unit is running in a non-steady state process, a plurality of sets of operating parameters are collected within a certain continuous time to obtain a plurality of sets of operating parameters.

3. The online integrated rapid detection method for an air conditioner outdoor unit according to claim 1, characterized in that, The set of operating parameters at least includes two types of inlet and outlet temperature, s terminal temperature, voltage, current, medium pressure, noise and power of the to-be-detected air conditioner outdoor unit.

4. The online integrated rapid detection method for an air conditioner outdoor unit according to claim 1, characterized in that, In step S3, the step of judging the overall performance of the to-be-detected air conditioner outdoor unit based on the operation value comprises: comparing the size of a preset threshold value and the operation value: when the operation value is less than the preset threshold value, it is determined that the to-be-detected air conditioner outdoor unit is faulty; when the operation value is greater than or equal to the preset threshold value, it is determined that the to-be-detected air conditioner outdoor unit is qualified.

5. The online integrated rapid detection method for an air conditioner outdoor unit according to claim 1, characterized in that, In step S4, the step of assigning weight values to the overall evaluation result and the single parameter evaluation result comprises: the weight value corresponding to the overall evaluation result is greater than the weight value corresponding to each single parameter evaluation result.

6. The online integrated rapid detection method for an air conditioner outdoor unit according to claim 1, characterized in that, In step S4, after assigning values to the overall evaluation result and the single parameter evaluation result respectively, the final data fusion calculation is performed using the following formula: wherein, V is the overall evaluation result after the assignment, Q is the single parameter evaluation result after the assignment, S is the comprehensive state discrimination result for the state of the air conditioner to be measured, The detection system comprises: 1 is a weight value given to the overall evaluation result of the air conditioner, a preprocessing module for preprocessing a plurality of sets of operating parameters of a to-be-detected air conditioner outdoor unit to obtain a corresponding set of data vectors; i is the single parameter discrimination result for the state of the air conditioner to be measured, i is a weight value given to the single parameter discrimination result.

7. A detection system for implementing the online integrated rapid detection method of the air conditioner outdoor unit according to any one of claims 1-6, characterized in that, a first data fusion processing module for performing preliminary data fusion processing on the set of data vectors respectively according to steps S21-S22 to generate normalization parameters and transmit them to a core data fusion processing module; a second data fusion processing module for comparing the size of each normalization parameter and its corresponding standard parameter to obtain a single parameter evaluation result of the to-be-detected air conditioner outdoor unit; also for performing weighted average probability value fusion operation on the normalization parameters according to the corresponding formula, and judging the overall performance of the to-be-detected air conditioner outdoor unit based on the operation value to obtain an overall evaluation result; a third data fusion processing module for assigning weight values to the overall evaluation result and the single parameter evaluation result respectively, and then performing final data fusion calculation to obtain a comprehensive state discrimination result of the to-be-detected air conditioner outdoor unit. The processor executes the computer program to realize the steps of the detection method in any one of claims 1 to 6. ​ 8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, ​

Images